This document was prepared in R Markdown, then translated into html using the R package knitr. Press the buttons labelled Code to show or hide the R code used to produce each table, plot or statistical result. You can also select ‘Show all code’ in the top left corner.

Load R libraries (install first from CRAN or Bioconductor)

library(GOstats) # GO term hypergeometric tests - load early so it doesn't clash with dplyr::select etc
library(WGCNA) # Gene networks - needs 'impute' dependency: source("https://bioconductor.org/biocLite.R"); biocLite("impute")
library(RSQLite) # Access SQLite databases
library(reshape2) # data tidying (melt)
library(dplyr) # data tidying
library(tidyr) # data tidying
library(stringr) # string manipulation
library(ggplot2) # for plots
library(ggrepel) # for plots
library(ggdendro) # for plots
library(gridExtra) # for plots
library(RColorBrewer) # for plots
library(ggjoy) # for plots
library(gplots) # Venn diagram
library(ecodist) # for nmds
library(MuMIn) # for model comparison
library(sva) # for ComBat function; install via source("https://bioconductor.org/biocLite.R"); biocLite("sva")
library(pander) # for nice tables
library(kableExtra) # For scrollable tables

kable.table <- function(df) {
  kable(df, "html") %>%
  kable_styling() %>%
  scroll_box(height = "300px")
}

# Open database connections (Sasha uses SQL, Luke prefers dplyr)
db <- dbConnect(SQLite(), dbname="data/queen_pheromone.db")
my_db <- src_sqlite("data/queen_pheromone.db")

# These 4 samples should NOT be used (See below). They were also removed in all non-R analyses (e.g. differential gene expression analyses using EBseq)
bad.samples <- c("lf1", "ln1", "ln12", "lf12")

First let’s check for and remove strongly outlying samples

  # Define a function to get gene expression data for a given set of orthologous genes. We define orthologous genes as those that are each other's reciprocal best BLAST. The bad.samples argument can be used to remove some named samples. By default this function logs the expression data (using log10). It returns a list with two elements: the first element is a matrix of expression data (rows = samples, cols = genes), and the second is a data frame giving the species-specific names of the orthologous genes
make.OGGs <- function(species, bad.samples = NULL, log.data = T){
  
  # set up forward mappings, e.g. "am2bt", "am2lf", "am2ln"
  forward.mappings <- paste(species[1], "2", species[2:length(species)], sep = "")
  # and reverse mappings, e.g. "bt2am", "lf2am", "ln2am"
  backward.mappings <- paste(species[2:length(species)], "2", species[1], sep = "")
  items <- list() # declare empty list

  for(i in 1:length(forward.mappings)){
    
    # make a table with 3 columns: first column has species 1 gene,
    # second column has species 2 gene in forward mapping,
    # third column has species 2 gene in reverse mapping (this can be NA, or different to col 2)
    # we want the rows where cols 2 and 3 are the same, indicating reciprocity in the BLAST
    focal <- left_join(
      tbl(my_db, forward.mappings[i]) %>% 
        dplyr::select(-evalue), # get the two mappings and 
      tbl(my_db, backward.mappings[i]) %>% 
        dplyr::select(-evalue), # merge by species 1 column
      by = species[1]
    ) %>% 
      collect(n=Inf) %>% as.data.frame  # collect it all and convert to df
    
    # Get the RBB rows, and keep the two relevant columns
    focal <- focal[!is.na(focal[,3]), ]
    items[[i]] <- focal[focal[,2] == focal[,3], 1:2] 
  }
  rbbs <- items[[1]] # If 3 or 4 species, successively merge the results
  if(length(items) > 1) rbbs <- left_join(rbbs, items[[2]], by = species[1])
  if(length(items) > 2) rbbs <- left_join(rbbs, items[[3]], by = species[1])
  
  # Throw out species1 genes that do not have a RBB in all species
  rbbs <- rbbs[complete.cases(rbbs), ]
  names(rbbs) <- gsub("[.]x", "", names(rbbs)) # tidy the row and column names
  rownames(rbbs) <- NULL

  # Make sure the columns are ordered as in 'species'
  rbbs <- rbbs[, match(names(rbbs), species)]

  # We know have a list of the names of all the ortholgous genes in each species
  # Now we use these names to look up the gene expression data for each ortholog
  expression.tables <- paste("rsem_", species, sep = "")
  
  for(i in 1:length(species)){
    focal.expression <- tbl(my_db, expression.tables[i]) %>% 
      collect(n=Inf) %>% as.data.frame()
    names(focal.expression)[names(focal.expression) == "gene"] <- species[i]
    rbbs <- left_join(rbbs, focal.expression, by = species[i])
  }
  gene.name.mappings <- rbbs[, names(rbbs) %in% species] # save gene name mappings in separate DF
  
  rownames(rbbs) <- rbbs[,1] # Use the gene names for species 1 as row names
  rbbs <- rbbs[, !(names(rbbs) %in% species)] # remove gene name columns 
  rbbs <- t(as.matrix(rbbs))

  if(log.data) rbbs <- log10(1 + rbbs)
  if(!is.null(bad.samples)) rbbs <- rbbs[!(rownames(rbbs) %in% bad.samples), ]
  
  # Discard genes where NAs appear
  gene.name.mappings <- gene.name.mappings[!(is.na(colSums(rbbs))), ]
  rbbs <- rbbs[, !(is.na(colSums(rbbs)))]

  # discard genes where expression is zero for all samples in 1 or more species
  spp <- str_replace_all(rownames(rbbs), "[:digit:]", "")
  to.keep <- rep(TRUE, ncol(rbbs))
  for(i in 1:ncol(rbbs)){
   if(min(as.numeric(tapply(rbbs[,i], spp, sum))) == 0) to.keep[i] <- FALSE
 }
rbbs <- rbbs[, to.keep]
gene.name.mappings <- gene.name.mappings[to.keep, ]

  list(tpm = rbbs, gene.mappings = gene.name.mappings)
}

4 of the Lasius samples are highly different to all of the rest

Closer inspection reveals that they have zeros for many of the transcripts, so perhaps they had low abundance libraries.

set.seed(1) # nmds involves random numbers, so make this plot reproducible
expression.data <- make.OGGs(c("am", "bt", "ln", "lf"))[[1]]
treatments <- tbl(my_db, "treatments") %>% as.data.frame()

shhh <- capture.output(nmds.output <- dist(expression.data) %>% nmds())
data.frame(id = rownames(expression.data), nmds.output$conf[[length(nmds.output$conf)]], stringsAsFactors = F) %>%
  left_join(treatments, by = "id") %>% 
  rename(Species = species, Treatment = treatment) %>%
  ggplot(aes(X1,X2, shape = Species)) + 
  geom_point(aes(colour = Treatment)) + 
  geom_text_repel(aes(label = id), size=3.6) + 
  xlab("NMDS 1") + ylab("NMDS 2")



Figure S1: After reducing the transcriptome data to two axes using non-metric multidimensional scaling, four Lasius samples are clear outliers.

set.seed(1) # nmds involves random numbers, so make this plot reproducible
expression.data <- make.OGGs(c("am", "bt", "ln", "lf"), bad.samples = bad.samples)[[1]]

shhh <- capture.output(nmds.output <- dist(expression.data) %>% nmds())
data.frame(id = rownames(expression.data), 
           nmds.output$conf[[length(nmds.output$conf)]], 
           stringsAsFactors = F) %>%
  left_join(treatments, by = "id") %>%
  rename(Species = species, Treatment = treatment) %>% 
  ggplot(aes(X1,X2)) + 
  geom_point(aes(shape = Species, colour = Treatment)) + 
  geom_text_repel(aes(label = id), size=3.6) + 
  xlab("NMDS 1") + ylab("NMDS 2")



Figure S2: With the four problematic samples removed, the samples cluster according to species with no obvious outliers.

Table of sample sizes

Table S1: Number of sequencing libraries for each combination of species and treatment, after removing the four problematic libraries. Each library was prepared from a pool of workers, taken from the same colony.

sample.size.table <- treatments[treatments$id %in% rownames(expression.data),] %>% 
  group_by(species, treatment) %>% 
  summarise(n = n()) %>% as.data.frame()
names(sample.size.table) <- c("Species", "Treatment", "Number of RNAseq libraries")
sample.size.table %>% pander()
Species Treatment Number of RNAseq libraries
am Control 3
am QP 3
bt Control 5
bt QP 5
lf Control 7
lf QP 6
ln Control 5
ln QP 5

Lists of significantly differentially expressed genes

apis.de <- suppressMessages(tbl(my_db, "ebseq_padj_gene_am") %>% 
  select(gene, PostFC) %>% 
    left_join(tbl(my_db, "bee_names")) %>% 
    collect() %>% 
  mutate(PostFC = round(log2(PostFC), 3)) %>% 
    select(gene, name, PostFC) %>% 
    rename(Gene=gene, Name=name, Log2_FC = PostFC) %>% 
    arrange(-abs(Log2_FC))) %>% as.data.frame()

bombus.de <- suppressMessages(tbl(my_db, "ebseq_padj_gene_bt") %>% 
  select(gene, PostFC) %>% 
    left_join(tbl(my_db, "bt2am") %>% rename(gene=bt)) %>% 
    left_join(tbl(my_db, "bee_names") %>% rename(am=gene)) %>% 
    collect() %>%
   mutate(PostFC = round(log2(PostFC), 3), name = replace(name, is.na(name), " "), 
          am = replace(am, is.na(am), " ")) %>% 
  select(gene, am, name, PostFC) %>% 
    rename(Gene=gene, Apis_BLAST=am, Name=name, Log2_FC = PostFC) %>% 
    arrange(-abs(Log2_FC))) %>% as.data.frame()

flavus.de <- suppressMessages(tbl(my_db, "ebseq_padj_gene_lf") %>% 
  select(gene, PostFC) %>% 
    left_join(tbl(my_db, "lf2am") %>% rename(gene=lf)) %>% 
    left_join(tbl(my_db, "bee_names") %>% rename(am=gene)) %>% 
    collect() %>%
   mutate(PostFC = round(log2(PostFC), 3), name = replace(name, is.na(name), " "), 
          am = replace(am, is.na(am), " ")) %>% 
  select(gene, am, name, PostFC) %>% 
    rename(Gene=gene, Apis_BLAST=am, Name=name, Log2_FC = PostFC) %>%
    arrange(-abs(Log2_FC))) %>% as.data.frame()

niger.de <- suppressMessages(tbl(my_db, "ebseq_padj_gene_ln") %>% 
  select(gene, PostFC) %>% 
    left_join(tbl(my_db, "ln2am") %>% rename(gene=ln)) %>% 
    left_join(tbl(my_db, "bee_names") %>% rename(am=gene)) %>% 
    collect() %>%
   mutate(PostFC = round(log2(PostFC), 3), name = replace(name, is.na(name), " "), 
          am = replace(am, is.na(am), " ")) %>% 
  select(gene, am, name, PostFC) %>% 
    rename(Gene=gene, Apis_BLAST=am, Name=name, Log2_FC = PostFC) %>% 
    arrange(-abs(Log2_FC))) %>% as.data.frame()

names(apis.de) <- gsub("_", " ", names(apis.de))
names(bombus.de) <- gsub("_", " ", names(bombus.de))
names(flavus.de) <- gsub("_", " ", names(flavus.de))
names(niger.de) <- gsub("_", " ", names(niger.de))

DE genes for Apis mellifera

Table S2: List of the 322 significantly differentially expressed genes (EBseq; p < 10-5) in Apis mellifera, listed in order of fold change in gene expression on a Log\(_2\) scale. Positive fold change values indicate higher expression in the control, while negative values indicate higher expression in the queen pheromone treatment.

kable.table(apis.de)
Gene Name Log2 FC
GB55204 Major royal jelly protein 3 6.480
GB51373 bypass of stop codon protein 1-like 5.385
GB50604 uncharacterized protein LOC724113 3.775
102655911 uncharacterized protein LOC102655911 -3.376
GB49819 branched-chain-amino-acid aminotransferase, cytosolic-like 2.657
102656917 uncharacterized LOC102656917, transcript variant X1 2.609
GB54417 dehydrogenase/reductase SDR family member 11-like isoform X1 2.242
GB45565 chymotrypsin-2 2.052
GB53886 protein G12-like isoform X4 1.983
100576536 uncharacterized protein LOC100576536 1.945
GB41540 venom carboxylesterase-6-like -1.721
GB54690 uncharacterized protein LOC408547 -1.583
GB54150 uncharacterized protein LOC408462 -1.560
GB43639 uncharacterized protein LOC100577506 isoform X1 -1.557
GB49548 serine/threonine-protein phosphatase 2B catalytic subunit 3-like isoform X11 -1.455
GB49878 probable cytochrome P450 6a14 isoformX1 1.393
GB53414 serine/threonine-protein kinase ICK-like isoform X2 1.357
102654781 protein G12-like 1.324
102656058 uncharacterized protein PF11_0213-like -1.311
GB53957 U6 snRNA-associated Sm-like protein LSm1-like 1.276
GB50413 protein TBRG4-like isoform X1 -1.261
102653931 uncharacterized LOC102653931, transcript variant X2 -1.258
GB53876 interaptin-like -1.209
GB42705 protein archease-like 1.184
101664701 PI-PLC X domain-containing protein 1-like isoform X1 1.143
GB42523 uncharacterized LOC100577781, transcript variant X2 -1.130
102654405 protein G12-like 1.115
100578075 uncharacterized LOC100578075 -1.110
GB52251 multifunctional protein ADE2, transcript variant X2 1.088
GB40764 uncharacterized protein LOC414021 isoform X7 -1.086
GB55648 Down syndrome cell adhesion molecule-like protein Dscam2-like isoform X7 -1.084
726446 uncharacterized protein LOC726446 -1.063
GB54467 probable G-protein coupled receptor 52 isoform 1 -1.060
GB46985 60S ribosomal protein L12 isoform X1 1.045
GB55191 uncharacterized protein LOC100576289 -1.045
GB54890 kynurenine 3-monooxygenase isoform X2 1.016
GB55640 retinol dehydrogenase 12-like -1.006
724802 protein Asterix-like 0.996
GB40010 titin-like isoform X2 -0.967
102654949 uncharacterized protein LOC102654949 0.967
GB43234 histone deacetylase 5 isoform X8 -0.965
GB52266 furin-like protease 2-like -0.927
GB41706 ice-structuring glycoprotein-like -0.926
GB42673 retinol dehydrogenase 10-A-like isoform X4 0.923
GB55030 uncharacterized protein LOC725074 0.921
551123 RNA-binding protein Musashi homolog Rbp6-like isoform X1 -0.920
409728 40S ribosomal protein S5 isoform X1 0.917
GB45028 venom dipeptidyl peptidase 4 -0.898
GB53422 ufm1-specific protease 1-like isoform X2 0.892
GB48933 methenyltetrahydrofolate synthase domain-containing protein-like -0.876
GB53077 cysteine-rich protein 1-like 0.871
GB41301 annexin-B9-like 0.862
GB51748 dentin sialophosphoprotein -0.861
102654594 WD repeat-containing protein 18-like 0.852
GB50356 60S acidic ribosomal protein P2 0.837
GB44091 LOW QUALITY PROTEIN: uncharacterized protein LOC408779 -0.836
GB41151 protein MNN4-like -0.834
409202 ribosomal protein S9, transcript variant X2 0.834
GB44340 small ubiquitin-related modifier 3 isoform 1 0.833
GB49173 4-aminobutyrate aminotransferase, mitochondrial-like isoform X2 -0.826
GB40769 dehydrogenase/reductase SDR family member 11-like 0.823
GB54243 LOW QUALITY PROTEIN: carbonyl reductase [NADPH] 1-like 0.819
724531 40S ribosomal protein S28-like 0.812
GB51744 uncharacterized protein LOC724439 0.811
GB51947 uncharacterized protein LOC724835 isoform X2 -0.807
GB40875 60S ribosomal protein L10 isoform X1 0.806
102655694 glutathione S-transferase-like 0.803
GB55827 40S ribosomal protein S21-like isoform X1 0.801
102654426 60S ribosomal protein L18-like 0.801
GB49988 SRR1-like protein-like isoform X2 -0.800
GB55963 uncharacterized protein LOC725224 isoform X1 -0.797
GB50867 cell differentiation protein RCD1 homolog isoform X2 0.794
GB43256 ATP-binding cassette sub-family D member 1-like 0.792
GB41211 ATP-binding cassette sub-family E member 1 0.787
GB52314 gamma-tubulin complex component 4 -0.785
102654251 uncharacterized protein LOC102654251 -0.782
726860 cytochrome b5-like isoform 1 0.778
GB46039 tubulin alpha-1 chain-like 0.773
GB53358 protein transport protein Sec61 subunit gamma-like isoform X3 0.768
GB48699 60S ribosomal protein L11-like 0.767
GB44311 actin related protein 1 0.762
102655603 transmembrane emp24 domain-containing protein 7-like 0.762
GB49170 40S ribosomal protein S15Aa-like isoform 1 0.758
GB47736 alkyldihydroxyacetonephosphate synthase-like 0.753
GB49013 RNA-binding protein 8A 0.752
724485 probable small nuclear ribonucleoprotein E-like 0.749
GB53000 ubiquitin-60S ribosomal protein L40 isoform 2 0.749
725936 titin-like -0.748
GB50158 60S ribosomal protein L4 isoform 1 0.748
GB52432 KN motif and ankyrin repeat domain-containing protein 3-like isoform X3 -0.746
724757 histone H4-like 0.745
GB53219 40S ribosomal protein S17 0.742
100577623 putative uncharacterized protein DDB_G0282133-like isoform X2 -0.742
GB51038 60S ribosomal protein L23 0.739
GB40284 cytochrome P450 6a2 0.737
GB50709 40S ribosomal protein S19a 0.735
GB50977 probable tubulin polyglutamylase TTLL2-like -0.734
GB42537 40S ribosomal protein S15 0.734
GB42467 phospholipase B1, membrane-associated-like isoform X2 0.733
GB41886 protein transport protein Sec61 subunit alpha isoform 2 0.729
GB51201 40S ribosomal protein S12 isoform X1 0.724
GB55183 ankyrin repeat domain-containing protein SOWAHB-like isoform X5 -0.724
GB54814 60S ribosomal protein L31 isoform 1 0.721
GB49159 probable nuclear transport factor 2-like isoform 3 0.717
GB52512 60S ribosomal protein L28 0.714
GB41142 probable dolichyl pyrophosphate Glc1Man9GlcNAc2 alpha-1,3-glucosyltransferase-like isoform X2 0.712
GB51359 60S ribosomal protein L27a isoform X1 0.710
GB50519 transmembrane emp24 domain-containing protein eca-like 0.710
GB47638 ER membrane protein complex subunit 3-like 0.705
GB51046 probable signal peptidase complex subunit 2-like 0.701
GB54973 selT-like protein-like isoform 1 0.693
GB44661 intracellular protein transport protein USO1 isoform X9 -0.691
GB53953 mitochondrial coenzyme A transporter SLC25A42-like isoformX1 -0.688
GB48289 uncharacterized protein LOC726292 isoform X1 0.688
GB47808 DEP domain-containing protein 5 isoform X4 -0.685
GB45937 intracellular protein transport protein USO1 isoform X2 -0.684
GB53750 UPF0454 protein C12orf49 homolog isoform X2 0.682
GB50455 ubiquitin-conjugating enzyme E2-17 kDa-like 0.676
GB42356 arginine-glutamic acid dipeptide repeats protein-like -0.675
GB51072 40S ribosomal protein S4-like isoform 1 0.669
GB55268 43 kDa receptor-associated protein of the synapse homolog isoform X3 -0.669
GB43086 uncharacterized protein LOC726486 0.668
102655259 5-methylcytosine rRNA methyltransferase NSUN4-like isoform X1 -0.667
GB55639 40S ribosomal protein S3 0.666
GB41159 bifunctional dihydrofolate reductase-thymidylate synthase 0.665
GB42354 ATP-dependent Clp protease ATP-binding subunit clpX-like, mitochondrial-like isoform X4 -0.663
GB42696 60S ribosomal protein L35a isoform X3 0.656
GB42088 40S ribosomal protein S29-like isoform X2 0.652
GB53948 uncharacterized protein LOC410057 isoform X1 -0.651
GB47553 electron transfer flavoprotein subunit alpha, mitochondrial-like isoform 1 0.650
100577163 slit homolog 2 protein-like 0.650
GB52627 protein pigeon-like -0.650
GB54020 apolipoprotein D-like 0.650
102655440 uncharacterized protein LOC102655440 -0.649
GB51009 T-complex protein 1 subunit delta-like isoform 1 0.649
GB49583 40S ribosomal protein S14 0.647
GB41039 60S ribosomal protein L17 isoform 1 0.647
GB46627 paraplegin-like -0.645
GB54174 E3 ubiquitin-protein ligase RING1 isoform 1 0.643
GB41240 aquaporin AQPAn.G-like isoform X3 -0.641
GB51440 proteoglycan 4-like -0.641
GB45433 small ribonucleoprotein particle protein B 0.638
GB51603 peptidyl-alpha-hydroxyglycine alpha-amidating lyase 1-like isoform X5 -0.638
100191002 ribosomal protein L41 0.638
GB43989 serine-threonine kinase receptor-associated protein-like 0.637
GB53799 proteasome subunit alpha type-2 0.636
GB43141 uncharacterized protein LOC413428 -0.636
GB44999 chascon-like -0.633
GB49154 bcl-2-related ovarian killer protein homolog A 0.632
GB50189 epsilon-sarcoglycan -0.630
GB41150 40S ribosomal protein S2 isoform 2 0.628
GB50917 60S acidic ribosomal protein P1 0.627
GB48201 39S ribosomal protein L53, mitochondrial 0.627
GB44575 ankyrin repeat and zinc finger domain-containing protein 1-like isoform X1 -0.626
GB46776 40S ribosomal protein S11 isoform X1 0.624
GB49789 28S ribosomal protein S29, mitochondrial isoformX1 -0.621
GB46750 40S ribosomal protein S16 0.620
GB44749 60S ribosomal protein L9 0.618
GB44931 evolutionarily conserved signaling intermediate in Toll pathway, mitochondrial-like -0.613
GB46845 60S ribosomal protein L37a 0.611
GB43379 membrane-bound transcription factor site-2 protease-like 0.609
GB45369 receptor of activated protein kinase C 1, transcript variant X3 0.606
GB52698 synaptobrevin-like isoformX1 0.605
724829 immediate early response 3-interacting protein 1-like isoform X1 0.605
GB49536 gamma-secretase subunit Aph-1 0.604
GB55628 probable RNA-binding protein EIF1AD-like isoform X1 0.603
GB50832 THO complex subunit 4-like 0.602
GB50929 mitochondrial import receptor subunit TOM40 homolog 1-like isoform 1 0.601
GB51065 40S ribosomal protein S10-like isoform 1 0.601
GB54984 chromatin complexes subunit BAP18-like isoform X1 0.600
GB43180 minor histocompatibility antigen H13-like 0.597
GB49365 gamma-secretase subunit pen-2 isoform 1 0.595
GB51543 60S ribosomal protein L13a isoform 2 0.594
GB54341 RNA-binding protein 33-like -0.594
102655912 L-aminoadipate-semialdehyde dehydrogenase-phosphopantetheinyl transferase-like 0.593
GB53420 uncharacterized protein LOC100576355 isoformX2 -0.591
GB48370 ATP-binding cassette sub-family B member 7, mitochondrial isoform X1 -0.591
726369 peptidyl-tRNA hydrolase 2, mitochondrial-like isoform 1 -0.591
GB46478 tectonin beta-propeller repeat-containing protein isoform X1 -0.591
GB42736 TM2 domain-containing protein CG10795-like 0.588
GB49087 formin-binding protein 1 homolog isoform X7 -0.588
GB50753 uncharacterized LOC408705 -0.586
GB46123 endonuclease G, mitochondrial-like -0.586
GB48574 thioredoxin-2 isoform 1 0.586
GB43232 transmembrane protein 222-like isoform 1 0.586
GB45285 eukaryotic translation initiation factor 3 subunit F-like 0.584
GB44631 uroporphyrinogen-III synthase-like 0.582
GB49994 60S ribosomal protein L26 0.581
GB52563 ATP-dependent helicase brm -0.579
GB54723 uncharacterized protein LOC726790 isoform X1 -0.578
GB53668 translocator protein-like 0.577
GB45374 40S ribosomal protein S23-like 0.576
GB46984 ribonuclease UK114-like isoform 1 0.572
102655352 uncharacterized protein LOC102655352 -0.572
GB45037 beta-lactamase-like protein 2-like isoform X2 -0.572
GB52107 tubulin alpha-1 chain-like 0.571
GB54139 flocculation protein FLO11-like -0.565
410017 protein OPI10 homolog 0.564
GB49177 60S ribosomal protein L27 isoform X2 0.557
GB54221 transmembrane protein 50A-like 0.556
GB54979 60S ribosomal protein L21 0.555
GB48111 proteasome subunit beta type-1 0.552
GB48745 5’-nucleotidase domain-containing protein 3-like -0.550
GB47079 hexokinase type 2-like isoform X3 -0.549
GB47441 V-type proton ATPase 21 kDa proteolipid subunit-like 0.549
GB41207 26S proteasome non-ATPase regulatory subunit 14 0.549
GB50274 transitional endoplasmic reticulum ATPase TER94 0.544
GB51683 annexin-B9-like isoform X1 0.544
GB54952 proteasome subunit alpha type-1-like 0.543
GB52253 protein PRRC2C-like isoform X2 -0.542
GB41648 protein chibby homolog 1-like 0.542
GB41363 26S protease regulatory subunit 6B isoform 1 0.541
GB53247 transmembrane emp24 domain-containing protein-like 0.541
GB48983 RING finger protein 121-like isoform X3 0.541
GB50873 60S ribosomal protein L30 isoform 1 0.540
GB54255 uncharacterized protein LOC551488 0.540
GB48810 60S ribosomal protein L8 0.537
GB41894 uncharacterized protein LOC411277 isoform X28 -0.536
GB49021 cuticular protein precursor 0.536
GB50131 phosphatidate phosphatase PPAPDC1A-like isoform X2 0.535
GB41811 filaggrin-like isoform X3 -0.534
GB51484 protein mago nashi 0.528
GB46705 muscle M-line assembly protein unc-89 isoform X5 -0.526
GB45978 dynein light chain Tctex-type isoform X2 0.526
GB43449 signal recognition particle 9 kDa protein 0.526
GB48150 actin-related protein 2/3 complex subunit 1A 0.525
GB54854 proteasome maturation protein-like 0.523
GB51545 dystrophin, isoforms A/C/F/G/H-like -0.523
GB49095 high affinity copper uptake protein 1-like isoformX1 0.523
GB43638 protein enhancer of sevenless 2B 0.522
GB51994 proteasome subunit beta type-6-like 0.520
GB53194 60S ribosomal protein L14 isoform X2 0.519
102656618 uncharacterized protein LOC102656618 isoform X1 -0.518
GB40539 40S ribosomal protein S20 0.518
GB41631 60S ribosomal protein L34 isoform X2 0.518
GB43938 cytosolic endo-beta-N-acetylglucosaminidase-like isoform X4 0.516
GB45878 tRNA-dihydrouridine(16/17) synthase [NAD(P)(+)]-like isoform X3 -0.516
GB44039 malate dehydrogenase, cytoplasmic-like isoform 1 0.513
GB55781 LOW QUALITY PROTEIN: uncharacterized protein LOC551170 -0.513
GB45526 eukaryotic translation initiation factor 6 isoform 1 0.510
GB52789 60S ribosomal protein L22 isoform 1 0.507
GB53626 myotrophin-like isoform 2 0.507
GB49364 splicing factor U2af 38 kDa subunit 0.505
GB44984 U5 small nuclear ribonucleoprotein 40 kDa protein-like isoform X1 0.504
GB50271 zinc transporter 1-like 0.503
GB49377 40S ribosomal protein S3a 0.501
GB50874 transcription factor Ken 2 -0.501
GB44147 60S ribosomal protein L15 0.498
GB46141 LOW QUALITY PROTEIN: vacuolar protein sorting-associated protein 29-like 0.494
GB51963 mitochondrial ribonuclease P protein 1 homolog -0.491
GB55901 ribosome biogenesis protein NSA2 homolog isoform X1 0.488
GB42036 protein SEC13 homolog isoform X2 0.485
GB40877 translocon-associated protein subunit delta 0.485
GB44205 proteasome subunit beta type-5-like 0.484
GB54151 uncharacterized protein LOC408463 isoform X12 -0.484
GB54590 polyadenylate-binding protein 1-like isoform X2 0.483
GB41157 RPII140-upstream gene protein-like -0.481
GB48423 small nuclear ribonucleoprotein F isoform 2 0.480
GB49608 protein angel-like isoform X1 -0.475
GB49812 RING-box protein 1A isoform X1 0.461
GB43697 mediator of RNA polymerase II transcription subunit 16 isoform X3 0.457
GB41553 Golgi phosphoprotein 3 homolog rotini-like isoform X1 0.455
GB43548 40S ribosomal protein SA 0.449
GB45181 probable Bax inhibitor 1 0.447
GB53086 alcohol dehydrogenase class-3 isoform X2 0.446
GB41724 uncharacterized protein LOC727081 -0.446
GB54533 protein unc-13 homolog D isoform X5 -0.445
GB40882 40S ribosomal protein S13 isoform X1 0.445
GB50230 V-type proton ATPase subunit e 2-like 0.445
102654691 protein translation factor SUI1 homolog 0.445
GB51787 myosin light chain alkali-like isoform X5 0.444
GB41908 PERQ amino acid-rich with GYF domain-containing protein CG11148-like isoform X3 -0.443
GB53138 inorganic pyrophosphatase-like 0.437
GB48250 putative gamma-glutamylcyclotransferase CG2811-like isoform X4 0.436
GB46763 excitatory amino acid transporter 3 0.436
GB53415 WW domain-binding protein 2-like isoform X1 0.432
GB47606 ER membrane protein complex subunit 4-like isoform 1 0.431
GB42675 adenylate cyclase type 2-like -0.430
GB44312 hydroxyacylglutathione hydrolase, mitochondrial-like isoform X2 0.428
102654127 neurochondrin homolog -0.423
GB47938 uncharacterized protein LOC412825 isoform X1 -0.421
GB55056 spermatogenesis-associated protein 20 isoform X2 -0.420
GB41084 60S ribosomal protein L38 0.412
GB47810 regulator of gene activity protein isoform X3 0.410
GB40946 serine/threonine-protein phosphatase 2A 65 kDa regulatory subunit A alpha isoform-like isoform X1 0.409
GB42780 CCHC-type zinc finger protein CG3800-like isoform X3 0.409
GB43229 GTP-binding nuclear protein Ran isoform X1 0.407
GB50244 NHL repeat-containing protein 2 isoform X4 -0.406
GB45684 protein spire-like isoform X4 -0.406
GB52073 probable citrate synthase 1, mitochondrial-like -0.402
GB45856 protein GPR107-like isoform X4 0.401
GB47542 eukaryotic translation initiation factor 3 subunit J isoform 1 0.399
GB53243 LOW QUALITY PROTEIN: probable phosphorylase b kinase regulatory subunit beta-like -0.395
GB55892 glutamate-rich WD repeat-containing protein 1-like 0.395
GB43105 casein kinase II subunit alpha isoform X6 0.390
GB43537 probable 28S ribosomal protein S16, mitochondrial 0.388
GB44496 probable serine incorporator isoformX1 0.376
GB43855 LOW QUALITY PROTEIN: coatomer subunit beta’ 0.374
GB40073 COP9 signalosome complex subunit 8-like 0.373
GB47100 putative glutamate synthase [NADPH]-like isoform X4 -0.372
GB42786 microtubule-associated protein RP/EB family member 1-like isoform X4 0.372
GB54789 GMP synthase [glutamine-hydrolyzing] 0.371
GB40767 phosphoglycolate phosphatase-like -0.370
GB52212 polyubiquitin-A-like isoform X2 0.370
GB52256 60S ribosomal protein L5 0.370
GB50925 prostaglandin E synthase 2-like -0.360
GB53725 splicing factor 3B subunit 1-like isoform X2 -0.355
GB44870 zinc finger protein 706-like isoform X3 0.355
GB45375 rhomboid-7 isoform X1 0.346
GB45044 uncharacterized protein LOC409396 isoform X5 -0.334
GB50909 dual 3’,5’-cyclic-AMP and -GMP phosphodiesterase 11-like, transcript variant X4 -0.333
GB44907 myeloid leukemia factor isoform X3 0.331
GB44333 flocculation protein FLO11-like isoform X1 -0.322
GB46562 40S ribosomal protein S24-like isoform X2 0.321
GB45017 RNA pseudouridylate synthase domain-containing protein 2-like isoform X3 -0.317
GB48312 pre-mRNA-splicing factor RBM22-like 0.316
GB47103 elongation factor 1-beta’ 0.310
GB48207 proteasomal ubiquitin receptor ADRM1 homolog isoform X1 0.270
GB40887 V-type proton ATPase subunit E isoform 3 0.266
GB41152 uncharacterized protein C6orf106 homolog 0.213
GB45678 1-acylglycerol-3-phosphate O-acyltransferase ABHD5-like isoform X1 -0.192
GB44576 ester hydrolase C11orf54 homolog 0.189

DE genes for Bombus terrestris

Table S3: The single differentially expressed gene (EBseq; p < 10-5) in Bombus terrestris. Positive fold change values indicate higher expression in the control, while negative values indicate higher expression in the queen pheromone treatment. The second and third columns give the best BLAST hit for this gene in A. mellifera plus the name of the A. mellifera putative ortholog.

kable(bombus.de, "html") %>%
  kable_styling()
Gene Apis BLAST Name Log2 FC
100648170 GB48391 mucin-2-like 1.071

DE genes for Lasius flavus

Table S4: List of the 290 significantly differentially expressed genes (EBseq; p < 10-5) in Lasius flavus, listed in order of fold change in gene expression on a Log\(_2\) scale. Positive fold change values indicate higher expression in the control, while negative values indicate higher expression in the queen pheromone treatment. The second and third columns give the best BLAST hit for this gene in A. mellifera plus the name of the A. mellifera putative ortholog.

kable.table(flavus.de)
Gene Apis BLAST Name Log2 FC
TRINITY_DN19074_c0_g2 GB43902 hexaprenyldihydroxybenzoate methyltransferase, mitochondrial-like 7.514
TRINITY_DN2701_c0_g1 GB52729 aspartate–tRNA ligase, cytoplasmic 7.481
TRINITY_DN14108_c0_g2 7.468
TRINITY_DN36041_c0_g1 6.629
TRINITY_DN13621_c0_g1 6.549
TRINITY_DN18780_c0_g2 -6.440
TRINITY_DN14430_c0_g1 6.278
TRINITY_DN32671_c0_g2 6.121
TRINITY_DN14910_c0_g1 XP_016769216.1 5.800
TRINITY_DN19071_c0_g1 -5.776
TRINITY_DN5663_c0_g2 XP_006568418.2 -5.365
TRINITY_DN13527_c1_g3 5.259
TRINITY_DN2506_c0_g2 5.133
TRINITY_DN9902_c0_g2 5.069
TRINITY_DN6503_c0_g3 551397 28S ribosomal protein S18a, mitochondrial isoform 2 5.044
TRINITY_DN10699_c0_g1 4.901
TRINITY_DN5102_c0_g1 XP_016771437.1 4.901
TRINITY_DN6994_c0_g1 4.859
TRINITY_DN13376_c3_g2 4.858
TRINITY_DN9565_c0_g3 GB45250 uncharacterized protein LOC409595 4.811
TRINITY_DN1013_c0_g1 GB52059 eukaryotic translation initiation factor 4H-like isoform X1 4.709
TRINITY_DN11616_c0_g1 4.696
TRINITY_DN1845_c0_g2 GB52253 protein PRRC2C-like isoform X2 4.658
TRINITY_DN7242_c0_g1 -4.646
TRINITY_DN31547_c0_g3 4.613
TRINITY_DN13376_c3_g3 4.569
TRINITY_DN6298_c0_g3 4.553
TRINITY_DN2720_c0_g2 -4.522
TRINITY_DN2583_c0_g2 4.460
TRINITY_DN24980_c0_g3 -4.393
TRINITY_DN12959_c0_g3 4.390
TRINITY_DN4813_c0_g1 4.322
TRINITY_DN6331_c0_g2 4.303
TRINITY_DN10925_c0_g1 4.278
TRINITY_DN14174_c1_g3 4.233
TRINITY_DN23574_c0_g3 4.173
TRINITY_DN6054_c0_g1 XP_016771772.1 4.143
TRINITY_DN32287_c0_g1 4.133
TRINITY_DN1060_c0_g1 4.115
TRINITY_DN6965_c0_g3 4.097
TRINITY_DN5087_c0_g1 XP_003249576.2 4.069
TRINITY_DN10904_c0_g1 4.050
TRINITY_DN4900_c0_g1 4.049
TRINITY_DN14065_c0_g2 4.015
TRINITY_DN2102_c0_g6 GB40389 profilin 3.751
TRINITY_DN12195_c1_g3 102656074 reticulon-4-like isoform X6 3.710
TRINITY_DN2302_c0_g2 3.676
TRINITY_DN9563_c1_g3 XP_016770117.1 3.347
TRINITY_DN11562_c2_g1 XP_016769630.1 3.211
TRINITY_DN6503_c0_g2 551397 28S ribosomal protein S18a, mitochondrial isoform 2 3.210
TRINITY_DN3428_c0_g1 GB53155 maternal embryonic leucine zipper kinase-like 3.168
TRINITY_DN11833_c0_g2 3.162
TRINITY_DN1150_c0_g2 3.151
TRINITY_DN14156_c9_g2 XP_016769763.1 3.146
TRINITY_DN7447_c0_g1 GB10293 aubergine 3.125
TRINITY_DN12563_c0_g2 XP_016768561.1 3.097
TRINITY_DN19328_c0_g2 GB49105 ecdysteroid-regulated gene E74 isoform X10 2.921
TRINITY_DN19071_c0_g5 -2.920
TRINITY_DN3355_c0_g1 XP_016772030.1 2.912
TRINITY_DN1453_c0_g2 2.891
TRINITY_DN34334_c0_g1 -2.831
TRINITY_DN9365_c0_g1 2.823
TRINITY_DN2907_c0_g1 GB52114 protein trachealess-like isoform X7 2.821
TRINITY_DN29060_c0_g1 2.784
TRINITY_DN5450_c0_g3 2.778
TRINITY_DN6679_c1_g1 -2.777
TRINITY_DN13106_c0_g1 -2.766
TRINITY_DN6249_c0_g2 2.762
TRINITY_DN12570_c0_g2 XP_016772046.1 2.752
TRINITY_DN29060_c0_g2 -2.748
TRINITY_DN1453_c0_g1 2.718
TRINITY_DN4551_c0_g1 2.665
TRINITY_DN5934_c0_g2 2.664
TRINITY_DN21319_c0_g1 2.647
TRINITY_DN16415_c0_g2 2.644
TRINITY_DN6639_c0_g2 GB51740 CD63 antigen 2.628
TRINITY_DN8686_c0_g6 2.525
TRINITY_DN27412_c0_g1 2.511
TRINITY_DN7556_c0_g1 2.479
TRINITY_DN12097_c3_g11 2.467
TRINITY_DN19324_c0_g1 2.464
TRINITY_DN5257_c0_g2 GB51614 probable methylthioribulose-1-phosphate dehydratase-like 2.451
TRINITY_DN3033_c0_g1 GB47735 endonuclease III-like protein 1-like 2.441
TRINITY_DN23065_c0_g1 2.434
TRINITY_DN30835_c0_g2 2.337
TRINITY_DN30278_c0_g7 2.328
TRINITY_DN13221_c0_g7 2.244
TRINITY_DN13083_c0_g1 2.202
TRINITY_DN12097_c3_g6 2.167
TRINITY_DN6372_c0_g3 2.154
TRINITY_DN13237_c2_g6 -2.137
TRINITY_DN3870_c0_g2 2.108
TRINITY_DN7016_c0_g2 GB47843 uncharacterized protein LOC100576559 isoform X2 1.972
TRINITY_DN12195_c1_g4 102656074 reticulon-4-like isoform X6 -1.727
TRINITY_DN15459_c0_g1 1.644
TRINITY_DN7587_c0_g2 GB52590 fatty acid synthase-like isoform 1 -1.363
TRINITY_DN3266_c0_g1 1.320
TRINITY_DN5353_c0_g1 GB43825 lysosomal aspartic protease 1.297
TRINITY_DN7865_c0_g1 XP_016770671.1 1.257
TRINITY_DN13667_c2_g1 1.226
TRINITY_DN9568_c0_g3 -1.068
TRINITY_DN8668_c0_g1 GB52590 fatty acid synthase-like isoform 1 -1.025
TRINITY_DN8075_c0_g1 -1.023
TRINITY_DN8944_c1_g2 -0.955
TRINITY_DN13195_c1_g2 0.950
TRINITY_DN11726_c1_g1 GB52590 fatty acid synthase-like isoform 1 -0.932
TRINITY_DN14247_c8_g2 GB52590 fatty acid synthase-like isoform 1 -0.926
TRINITY_DN61_c0_g1 GB45775 pancreatic triacylglycerol lipase-like isoform X2 -0.888
TRINITY_DN2623_c0_g1 GB43825 lysosomal aspartic protease 0.862
TRINITY_DN12575_c0_g1 GB55263 putative fatty acyl-CoA reductase CG5065-like -0.832
TRINITY_DN14020_c0_g1 GB46188 trichohyalin-like isoform X1 0.728
TRINITY_DN13013_c0_g1 XP_016768441.1 0.710
TRINITY_DN12756_c2_g1 0.691
TRINITY_DN9649_c0_g1 NP_001305411.1 0.685
TRINITY_DN13574_c1_g2 GB40681 elongation of very long chain fatty acids protein 1-like -0.679
TRINITY_DN9287_c0_g1 XP_016768964.1 0.671
TRINITY_DN13318_c0_g1 GB46888 alpha-methylacyl-CoA racemase-like -0.612
TRINITY_DN3111_c0_g1 0.588
TRINITY_DN13226_c0_g1 GB47475 protein lethal(2)essential for life-like isoform 1 0.586
TRINITY_DN5134_c0_g1 XP_016770229.1 0.578
TRINITY_DN12647_c0_g1 XP_016773029.1 -0.572
TRINITY_DN14059_c0_g1 XP_016768888.1 0.567
TRINITY_DN13252_c1_g1 GB50415 diacylglycerol kinase theta-like isoform X7 0.559
TRINITY_DN13742_c0_g1 GB46657 galactokinase-like -0.518
TRINITY_DN13982_c0_g1 XP_016769706.1 -0.517
TRINITY_DN32324_c0_g1 102656101 uncharacterized protein LOC102656101 0.517
TRINITY_DN12496_c0_g1 GB54423 uncharacterized protein LOC551958 0.511
TRINITY_DN11328_c0_g1 GB51479 ras guanine nucleotide exchange factor P-like isoform X3 0.509
TRINITY_DN6523_c0_g1 GB40976 heat shock protein 90 -0.504
TRINITY_DN12344_c0_g1 0.503
TRINITY_DN15124_c0_g1 0.500
TRINITY_DN12742_c1_g1 XP_016767680.1 0.490
TRINITY_DN11193_c0_g1 GB53045 ATP-binding cassette sub-family G member 1-like isoform X1 -0.481
TRINITY_DN10448_c0_g2 GB41603 PTB domain-containing adapter protein ced-6 isoform X2 -0.474
TRINITY_DN1154_c0_g1 0.474
TRINITY_DN14164_c3_g1 GB55490 uncharacterized protein LOC410793 -0.473
TRINITY_DN14136_c5_g1 GB55016 quinone oxidoreductase-like isoform X2 0.465
TRINITY_DN9952_c0_g1 GB43823 chemosensory protein 1 precursor 0.462
TRINITY_DN8450_c0_g1 GB46286 zinc carboxypeptidase A 1-like isoform X1 0.454
TRINITY_DN12807_c0_g1 XP_016769434.1 0.450
TRINITY_DN13250_c5_g1 GB45937 intracellular protein transport protein USO1 isoform X2 0.445
TRINITY_DN6544_c0_g1 GB52074 6-phosphogluconate dehydrogenase, decarboxylating -0.445
TRINITY_DN13581_c2_g2 GB42792 uncharacterized protein LOC409805 isoform X3 0.444
TRINITY_DN36181_c0_g1 0.442
TRINITY_DN2719_c0_g1 GB54446 arginine kinase isoform X2 0.441
TRINITY_DN13519_c0_g1 GB42797 protein takeout-like 0.440
TRINITY_DN7060_c0_g1 GB49607 lysosome-associated membrane glycoprotein 1-like isoform 2 -0.438
TRINITY_DN1392_c0_g1 GB44205 proteasome subunit beta type-5-like -0.434
TRINITY_DN10466_c0_g1 GB44431 26S protease regulatory subunit 4 isoform 1 -0.428
TRINITY_DN13148_c0_g1 GB44213 filamin-like 0.426
TRINITY_DN13702_c3_g1 XP_016769732.1 0.423
TRINITY_DN12417_c0_g2 GB45456 flocculation protein FLO11-like isoform X2 0.422
TRINITY_DN23399_c0_g1 0.417
TRINITY_DN11737_c0_g1 XP_016766478.1 -0.416
TRINITY_DN12348_c0_g1 GB44703 proteasome activator complex subunit 4-like -0.415
TRINITY_DN13581_c1_g3 XP_016767189.1 0.406
TRINITY_DN11774_c0_g1 XP_016772498.1 0.387
TRINITY_DN3048_c0_g1 GB40770 dehydrogenase/reductase SDR family member 11-like isoform X2 0.387
TRINITY_DN13700_c5_g3 GB42840 leukocyte receptor cluster member 8 homolog isoform X4 0.387
TRINITY_DN13455_c0_g1 GB45128 trifunctional enzyme subunit alpha, mitochondrial-like -0.380
TRINITY_DN14019_c2_g1 409060 neurofilament heavy polypeptide-like isoform X2 0.377
TRINITY_DN11786_c1_g1 GB51214 troponin T, skeletal muscle 0.374
TRINITY_DN9982_c0_g1 GB51787 myosin light chain alkali-like isoform X5 0.372
TRINITY_DN27322_c0_g1 GB40866 heat shock protein cognate 4 -0.369
TRINITY_DN5956_c0_g1 0.366
TRINITY_DN6208_c0_g1 GB49757 fatty acid binding protein 0.359
TRINITY_DN11594_c0_g1 GB52643 poly(U)-specific endoribonuclease homolog 0.355
TRINITY_DN9687_c0_g1 0.350
TRINITY_DN14119_c3_g1 726668 PDZ and LIM domain protein 3 isoform X7 0.348
TRINITY_DN5256_c0_g1 0.345
TRINITY_DN10396_c0_g1 GB42607 cytochrome b5-like isoform X1 -0.344
TRINITY_DN5623_c0_g1 GB54817 muscle-specific protein 20 0.343
TRINITY_DN10620_c0_g1 GB42732 long-chain-fatty-acid–CoA ligase 3-like isoform X2 -0.325
TRINITY_DN12788_c0_g1 XP_016771468.1 0.325
TRINITY_DN12757_c0_g1 GB55610 MOSC domain-containing protein 2, mitochondrial-like 0.324
TRINITY_DN10923_c0_g1 GB40141 venom serine carboxypeptidase -0.321
TRINITY_DN10232_c0_g1 -0.319
TRINITY_DN12105_c0_g1 XP_016768441.1 0.318
TRINITY_DN7549_c0_g1 XP_016768456.1 0.315
TRINITY_DN3036_c0_g1 GB52326 chemosensory protein 4 precursor 0.313
TRINITY_DN12756_c2_g4 XP_016770894.1 0.311
TRINITY_DN14002_c3_g1 XP_016770982.1 0.307
TRINITY_DN27284_c0_g1 GB50274 transitional endoplasmic reticulum ATPase TER94 -0.306
TRINITY_DN12138_c0_g1 GB47306 sulfhydryl oxidase 1-like 0.305
TRINITY_DN13865_c0_g1 GB47963 probable E3 ubiquitin-protein ligase HERC4-like isoform X3 0.302
TRINITY_DN8423_c0_g1 XP_016768214.1 -0.298
TRINITY_DN27569_c0_g1 GB52736 ATP synthase subunit beta, mitochondrial isoform X1 0.297
TRINITY_DN14286_c2_g1 GB54861 LOW QUALITY PROTEIN: counting factor associated protein D-like -0.294
TRINITY_DN14128_c1_g1 XP_006568818.2 0.291
TRINITY_DN11359_c0_g1 XP_016768872.1 -0.287
TRINITY_DN9072_c0_g1 XP_016768321.1 -0.287
TRINITY_DN28113_c0_g1 -0.285
TRINITY_DN10911_c0_g1 XP_016770213.1 -0.277
TRINITY_DN12726_c3_g1 GB42787 dentin sialophosphoprotein-like isoform X4 -0.274
TRINITY_DN6072_c0_g1 XP_016771431.1 -0.273
TRINITY_DN13789_c0_g2 XP_016767109.1 0.273
TRINITY_DN14037_c0_g1 XP_016767155.1 0.272
TRINITY_DN13738_c0_g1 XP_016772667.1 0.271
TRINITY_DN993_c0_g3 0.270
TRINITY_DN7531_c0_g3 GB51710 eukaryotic initiation factor 4A-like isoformX2 0.260
TRINITY_DN11232_c0_g1 GB40240 myosin regulatory light chain 2 0.258
TRINITY_DN12074_c1_g1 GB47462 protein disulfide-isomerase A3 isoform 2 -0.256
TRINITY_DN11684_c0_g1 GB55537 transketolase isoform 1 -0.248
TRINITY_DN14138_c2_g1 GB48850 fatty-acid amide hydrolase 2-B-like -0.248
TRINITY_DN13963_c1_g1 XP_016768450.1 0.247
TRINITY_DN12180_c0_g1 XP_016772046.1 0.246
TRINITY_DN13233_c1_g1 XP_016768217.1 -0.244
TRINITY_DN12080_c1_g1 XP_016769481.1 -0.241
TRINITY_DN11171_c0_g1 GB42468 phospholipase B1, membrane-associated-like isoform X1 -0.239
TRINITY_DN13982_c0_g3 XP_016769706.1 -0.237
TRINITY_DN14752_c0_g1 GB50123 myophilin-like 0.226
TRINITY_DN8270_c0_g1 GB43276 aminopeptidase N-like isoform X1 0.226
TRINITY_DN12844_c1_g1 GB47885 probable cytochrome P450 304a1 -0.224
TRINITY_DN11885_c1_g1 GB55598 troponin I isoform X23 0.218
TRINITY_DN8742_c0_g1 XP_016767150.1 -0.216
TRINITY_DN14111_c0_g1 GB46705 muscle M-line assembly protein unc-89 isoform X5 0.213
TRINITY_DN14002_c4_g1 0.212
TRINITY_DN7802_c0_g1 GB41358 elongation factor 1-alpha -0.210
TRINITY_DN14006_c0_g1 XP_016767101.1 -0.208
TRINITY_DN8847_c0_g1 GB46772 very-long-chain enoyl-CoA reductase-like -0.201
TRINITY_DN14179_c1_g1 GB40461 calreticulin -0.186
TRINITY_DN7523_c0_g1 -0.183
TRINITY_DN12909_c0_g1 XP_016770377.1 0.181
TRINITY_DN8174_c0_g1 GB47880 superoxide dismutase 1 -0.175
TRINITY_DN14199_c2_g1 -0.173
TRINITY_DN3676_c0_g2 GB49773 sequestosome-1 0.168
TRINITY_DN3648_c0_g1 GB45181 probable Bax inhibitor 1 -0.167
TRINITY_DN9738_c0_g1 GB44206 death-associated protein 1-like -0.167
TRINITY_DN3697_c0_g1 GB54368 prostaglandin E synthase 3-like isoform X2 -0.165
TRINITY_DN13223_c0_g1 GB54315 uncharacterized protein LOC724126 -0.157
TRINITY_DN9957_c0_g1 GB43831 ATP-binding cassette sub-family D member 3-like -0.157
TRINITY_DN1533_c0_g1 XP_392401.3 -0.155
TRINITY_DN12307_c0_g1 GB47029 uncharacterized protein LOC724558 -0.153
TRINITY_DN13021_c0_g1 XP_006571535.2 -0.144
TRINITY_DN11571_c0_g2 XP_001119981.3 -0.138
TRINITY_DN14152_c0_g10 XP_016771978.1 0.136
TRINITY_DN13002_c1_g1 XP_016767675.1 -0.131
TRINITY_DN13997_c1_g2 XP_016771269.1 0.130
TRINITY_DN7931_c0_g1 GB49321 D-arabinitol dehydrogenase 1-like -0.128
TRINITY_DN12756_c2_g5 XP_016770894.1 -0.126
TRINITY_DN1575_c0_g1 0.124
TRINITY_DN1616_c0_g1 GB41545 MD-2-related lipid-recognition protein-like 0.120
TRINITY_DN12630_c0_g1 GB45258 isocitrate dehydrogenase [NADP] cytoplasmic isoform 2 -0.119
TRINITY_DN14083_c3_g1 GB55263 putative fatty acyl-CoA reductase CG5065-like -0.117
TRINITY_DN4494_c0_g2 GB47990 tropomyosin-1-like 0.116
TRINITY_DN1524_c0_g1 GB46920 iron-sulfur cluster assembly enzyme ISCU, mitochondrial 0.115
TRINITY_DN13221_c0_g9 XP_016769341.1 0.107
TRINITY_DN13959_c2_g1 GB49688 peroxidase isoformX2 0.104
TRINITY_DN12634_c0_g1 GB43575 trehalase-like isoform X2 -0.093
TRINITY_DN13844_c1_g1 XP_016767538.1 -0.092
TRINITY_DN10322_c0_g1 XP_016769014.1 -0.088
TRINITY_DN13381_c0_g1 GB51633 protein HIRA homolog 0.084
TRINITY_DN12970_c0_g2 GB44208 WD repeat-containing protein 37-like isoform X4 0.083
TRINITY_DN3647_c0_g1 GB53550 heat shock protein beta-1-like isoform X3 -0.081
TRINITY_DN8558_c0_g1 GB46713 translation elongation factor 2-like isoform 1 -0.079
TRINITY_DN11372_c0_g1 GB53755 juvenile hormone esterase precursor 0.071
TRINITY_DN6049_c0_g1 0.068
TRINITY_DN10813_c0_g1 GB51753 uncharacterized protein LOC100576760 isoform X2 -0.066
TRINITY_DN10427_c0_g1 GB51782 carboxypeptidase Q-like isoform 1 -0.065
TRINITY_DN8685_c0_g4 GB43825 lysosomal aspartic protease -0.065
TRINITY_DN13047_c0_g1 XP_016768229.1 0.061
TRINITY_DN6208_c0_g2 GB49757 fatty acid binding protein -0.056
TRINITY_DN13652_c0_g1 GB42422 ADP/ATP translocase 0.054
TRINITY_DN13884_c0_g2 GB47405 neutral alpha-glucosidase AB-like isoform 2 0.051
TRINITY_DN13634_c0_g1 GB45913 protein lethal(2)essential for life-like -0.049
TRINITY_DN1723_c0_g1 GB52324 chemosensory protein 3 precursor 0.048
TRINITY_DN18895_c0_g1 GB55581 membrane-associated progesterone receptor component 1-like isoform 2 -0.044
TRINITY_DN8126_c0_g1 GB40779 transaldolase -0.044
TRINITY_DN10665_c0_g1 GB42829 juvenile hormone epoxide hydrolase 1 -0.042
TRINITY_DN8184_c0_g1 0.040
TRINITY_DN11577_c0_g1 GB55096 NADP-dependent malic enzyme isoform X3 0.040
TRINITY_DN18992_c0_g1 XP_016772082.1 0.039
TRINITY_DN11030_c0_g1 GB49240 aldehyde dehydrogenase, mitochondrial isoform 1 -0.038
TRINITY_DN11459_c0_g1 GB50598 aldose reductase-like isoform 1 -0.038
TRINITY_DN13961_c1_g3 GB52588 conserved oligomeric Golgi complex subunit 7 -0.037
TRINITY_DN12872_c0_g1 GB53333 V-type proton ATPase catalytic subunit A-like isoform X3 0.035
TRINITY_DN13271_c0_g1 GB40312 choline/ethanolamine kinase-like isoform X4 0.030
TRINITY_DN13702_c8_g1 GB47395 uncharacterized protein CG7816-like -0.030
TRINITY_DN13400_c0_g1 GB54421 uncharacterized protein DDB_G0287625-like 0.023
TRINITY_DN10682_c0_g1 GB50252 GTP-binding protein SAR1b-like isoform X4 -0.021
TRINITY_DN8055_c0_g1 -0.021
TRINITY_DN9151_c0_g1 GB45147 clavesin-2-like 0.021
TRINITY_DN11885_c3_g1 GB47880 superoxide dismutase 1 -0.019
TRINITY_DN12979_c1_g1 GB49347 prostaglandin reductase 1-like 0.013
TRINITY_DN14085_c1_g1 XP_016769919.1 -0.011
TRINITY_DN11118_c1_g1 GB44422 uncharacterized protein LOC412543 isoform X3 -0.010
TRINITY_DN14002_c1_g1 0.004
TRINITY_DN7306_c0_g2 XP_016769332.1 -0.004
TRINITY_DN13747_c0_g1 XP_016769944.1 -0.003
TRINITY_DN10790_c0_g1 0.000

DE genes for Lasius niger

Table S5: List of the 135 significantly differentially expressed genes (EBseq; p < 10-5) in Lasius niger, listed in order of fold change in gene expression on a Log\(_2\) scale. Positive fold change values indicate higher expression in the control, while negative values indicate higher expression in the queen pheromone treatment. The second and third columns give the best BLAST hit for this gene in A. mellifera plus the name of the A. mellifera putative ortholog.

kable.table(niger.de)
Gene Apis BLAST Name Log2 FC
XLOC_001009 5.916
RF55_9944 GB55171 major royal jelly protein 1 isoform X1 5.060
RF55_873 XP_016773511.1 4.638
XLOC_000784 3.626
RF55_874 XP_016766165.1 3.550
XLOC_016588 3.077
RF55_9436 2.813
RF55_3510 GB53672 failed axon connections isoform X2 -2.471
RF55_15864 -2.439
XLOC_020552 2.437
RF55_783 2.206
RF55_6001 -2.150
XLOC_013573 2.150
RF55_4870 XP_006563262.2 -2.031
XLOC_022706 -1.091
RF55_7689 XP_003250465.2 -1.030
RF55_19841 GB52590 fatty acid synthase-like isoform 1 -1.015
RF55_21338 GB52590 fatty acid synthase-like isoform 1 -0.923
RF55_13568 XP_006571191.2 0.882
RF55_2210 GB49869 microsomal triglyceride transfer protein large subunit isoform X1 -0.879
RF55_6639 GB48784 cytochrome c 0.779
RF55_15245 GB43617 uncharacterized membrane protein DDB_G0293934-like isoform X1 0.734
RF55_14443 GB51356 cytochrome P450 4G11 0.726
RF55_5140 XP_016767978.1 0.656
XLOC_003947 0.655
XLOC_019296 -0.643
XLOC_005895 -0.625
XLOC_010120 0.619
RF55_3431 GB47849 pyrroline-5-carboxylate reductase 2-like isoform X2 0.611
RF55_6542 GB52074 6-phosphogluconate dehydrogenase, decarboxylating -0.603
RF55_6567 552211 protein THEM6-like -0.597
RF55_11093 GB51174 uncharacterized protein DDB_G0284459-like 0.593
RF55_9960 GB52023 cytochrome P450 6AQ1 isoform X3 -0.584
RF55_14139 XP_016768457.1 0.561
RF55_16317 XP_016770827.1 -0.523
RF55_16054 GB55082 protein PBDC1-like 0.489
XLOC_004490 -0.474
RF55_9918 GB47885 probable cytochrome P450 304a1 0.470
XLOC_015751 -0.442
RF55_12610 GB40866 heat shock protein cognate 4 -0.432
RF55_11067 GB46772 very-long-chain enoyl-CoA reductase-like -0.431
RF55_6451 GB55598 troponin I isoform X23 0.430
RF55_10641 XP_016769078.1 -0.430
RF55_4656 GB42792 uncharacterized protein LOC409805 isoform X3 0.415
RF55_4036 GB44208 WD repeat-containing protein 37-like isoform X4 0.407
XLOC_002901 -0.398
RF55_16927 XP_006564499.2 0.394
RF55_4554 GB47990 tropomyosin-1-like 0.393
RF55_15079 GB41028 ATP synthase subunit alpha, mitochondrial isoform 1 0.375
RF55_3507 GB41333 DNA-directed RNA polymerase III subunit RPC1-like isoform X1 -0.375
RF55_5177 GB43902 hexaprenyldihydroxybenzoate methyltransferase, mitochondrial-like -0.368
RF55_13988 GB55263 putative fatty acyl-CoA reductase CG5065-like -0.362
RF55_10649 0.359
RF55_2038 GB51787 myosin light chain alkali-like isoform X5 0.350
RF55_3707 GB55537 transketolase isoform 1 -0.342
XLOC_005759 0.330
RF55_10912 GB47880 superoxide dismutase 1 -0.324
RF55_18605 XP_016770827.1 -0.315
RF55_17057 GB52590 fatty acid synthase-like isoform 1 -0.312
RF55_3648 XP_016768682.1 -0.310
RF55_5902 GB55302 trehalose transporter 1 isoform X6 0.308
RF55_12242 GB41912 trans-1,2-dihydrobenzene-1,2-diol dehydrogenase-like -0.286
RF55_10676 GB40240 myosin regulatory light chain 2 0.279
RF55_4654 GB45673 alpha-N-acetylgalactosaminidase-like 0.277
XLOC_012799 0.273
XLOC_018477 -0.268
RF55_6754 XP_016772080.1 0.254
RF55_3967 GB46039 tubulin alpha-1 chain-like -0.251
RF55_1582 GB45012 adenosylhomocysteinase-like 0.248
RF55_2761 XP_003249233.2 0.246
RF55_2493 GB45913 protein lethal(2)essential for life-like -0.244
RF55_15035 GB51356 cytochrome P450 4G11 -0.223
RF55_5799 GB50123 myophilin-like 0.216
RF55_5341 GB50508 fibrillin-2 -0.215
RF55_598 GB40021 probable serine/threonine-protein kinase clkA-like -0.215
RF55_5109 XP_016767675.1 -0.211
RF55_2407 XP_016768440.1 0.207
RF55_3343 GB46290 acetyl-coenzyme A synthetase-like -0.205
RF55_10752 XP_016771487.1 0.204
RF55_19196 GB41311 actin, indirect flight muscle-like 0.202
RF55_5837 GB43879 aquaporin AQPcic-like isoform X2 -0.191
RF55_13604 XP_016767981.1 0.185
RF55_3994 GB49175 4-hydroxyphenylpyruvate dioxygenase-like 0.181
RF55_18796 GB53412 fatty acid synthase-like -0.180
XLOC_001770 0.175
RF55_1934 GB54827 synaptotagmin 1 -0.169
RF55_5219 GB51753 uncharacterized protein LOC100576760 isoform X2 -0.163
RF55_778 GB42422 ADP/ATP translocase 0.154
RF55_10519 GB54446 arginine kinase isoform X2 0.141
RF55_364 0.137
RF55_2231 XP_016773593.1 -0.134
XLOC_008839 -0.132
RF55_5431 -0.129
RF55_5198 XP_016768517.1 0.124
RF55_11370 XP_016772844.1 -0.115
RF55_13251 GB52590 fatty acid synthase-like isoform 1 -0.113
RF55_6842 GB43052 paramyosin, long form-like 0.109
RF55_6077 GB54423 uncharacterized protein LOC551958 -0.108
RF55_6180 GB40758 icarapin-like 0.108
XLOC_005990 -0.099
RF55_10150 XP_016769706.1 0.099
RF55_1045 GB54861 LOW QUALITY PROTEIN: counting factor associated protein D-like -0.097
RF55_3186 XP_016770377.1 0.092
XLOC_020265 -0.089
XLOC_019117 -0.085
RF55_4175 GB44311 actin related protein 1 0.083
XLOC_016272 -0.079
RF55_5206 GB40735 fructose-bisphosphate aldolase-like isoform X1 0.071
RF55_4024 XP_016767817.1 0.069
RF55_9453 GB55096 NADP-dependent malic enzyme isoform X3 -0.067
RF55_8355 GB42809 translationally-controlled tumor protein homolog isoform 1 0.063
RF55_3575 XP_016768967.1 -0.062
XLOC_011290 0.061
RF55_5559 GB52107 tubulin alpha-1 chain-like 0.061
RF55_3308 -0.059
XLOC_020794 0.059
XLOC_018966 0.059
RF55_1104 XP_016769017.1 0.048
RF55_652 GB54354 uncharacterized protein DDB_G0274915-like isoform X2 0.045
RF55_3854 XP_006571125.2 -0.036
RF55_6873 GB47106 NADH-ubiquinone oxidoreductase 75 kDa subunit, mitochondrial -0.035
RF55_15158 GB42794 circadian clock-controlled protein-like isoform 1 -0.034
RF55_4888 GB40779 transaldolase 0.034
XLOC_019193 0.026
XLOC_013126 -0.025
XLOC_017016 0.025
XLOC_016458 -0.024
XLOC_013131 -0.013
RF55_10886 GB41427 catalase -0.012
XLOC_003165 -0.010
RF55_9333 GB49688 peroxidase isoformX2 0.008
XLOC_004885 -0.005
RF55_5677 GB46713 translation elongation factor 2-like isoform 1 0.004
RF55_14822 GB43823 chemosensory protein 1 precursor 0.004
RF55_11002 XP_016768909.1 0.002

Genes that are differentially expressed in multiple species

In the first pair of tables, we have simply listed the genes that showed statistically significant differential expression in two or more species. This method makes few false positives, but it likely misses many of true overlaps because our study has modest power to detect differential expression.

In the third table, we instead look for similarities between species using a method that ranks genes from most- to least- phermone sensitive based on log fold change, alleviating the problem of . To do this, we select the top n genes per species (where n = 100, 200 … 500), based on the absolute magnitude of the log fold-change response to queen pheromone, giving a list of the most pheromone-sensitive genes. We beleive that this alternative method likely produces fewer false negatives in our search for overlapping genes, at cost of getting more false positives.

# Define a function to test whether the overlap of two sets of differentially expressed genes, 
# drawn from a common pool (e.g. all the orthologs that were tested), is higher or lower than expected
# Inspiration for this code: https://stats.stackexchange.com/questions/10328/using-rs-phyper-to-get-the-probability-of-list-overlap
overlap.hypergeometric.test <- function(n.overlaps, num.sig1, num.sig2, num.genes, species){
  p.smaller <- phyper(n.overlaps, num.sig1, num.genes - num.sig1, num.sig2) 
  p.higher <- 1 - phyper(n.overlaps - 1, num.sig1, num.genes - num.sig1, num.sig2)
  output <- data.frame(Species = species,
                       Test = c("Overlap is lower than expected:",
                                  "Overlap is higher than expected:"),
                       p = c(p.smaller, p.higher))
  output[output$p == min(output$p), ]
}



# Apis and flavus
af.oggs <- make.OGGs(c("am", "lf"))[[2]] # Get the orthologous gene list
n.am <- (tbl(my_db, "ebseq_padj_gene_am") %>% 
           filter(gene %in% af.oggs$am) %>% 
           summarise(n=n()) %>% 
           as.data.frame())[1,1] # Count the number of diff expressed genes that appear in the OGG list
n.lf <- (tbl(my_db, "ebseq_padj_gene_lf") %>% 
           filter(gene %in% af.oggs$lf) %>% summarise(n=n()) %>% 
           as.data.frame())[1,1]
num.oggs.af <- nrow(af.oggs) # Count the orthologous genes
af.oggs <- suppressMessages(
  af.oggs %>% 
    filter(am %in% (tbl(my_db, "ebseq_padj_gene_am") %>% 
                      as.data.frame())[,1],
           lf %in% (tbl(my_db, "ebseq_padj_gene_lf") %>% 
                      as.data.frame())[,1]) %>% 
    mutate(Species = "Apis and L. flavus") %>% 
    left_join(tbl(my_db, "ebseq_gene_am") %>% 
                select(gene, PostFC) %>% 
                rename(am=gene), copy=T) %>% 
    rename(`Apis FC` = PostFC) %>%
    left_join(tbl(my_db, "ebseq_gene_lf") %>% 
                select(gene, PostFC) %>% 
                rename(lf=gene), copy=T) %>% 
    rename(`L. flavus FC` = PostFC) %>%
    left_join(tbl(my_db, "bee_names") %>% 
                rename(am=gene), copy=T))
num.overlap.af <- nrow(af.oggs) # Count the overlaps
test1 <- overlap.hypergeometric.test(num.overlap.af, 
                                     n.am, n.lf, 
                                     num.oggs.af, 
                                     "Apis and L. flavus") # Run the hypergeometric test


# Apis and niger
an.oggs <- make.OGGs(c("am", "ln"))[[2]] # Get the orthologous gene list
n.am <- (tbl(my_db, "ebseq_padj_gene_am") %>% 
           filter(gene %in% an.oggs$am) %>% 
           summarise(n=n()) %>% as.data.frame())[1,1] # Count the number of diff expressed genes that appear in the OGG list
n.ln <- (tbl(my_db, "ebseq_padj_gene_ln") %>% 
           filter(gene %in% an.oggs$ln) %>% 
           summarise(n=n()) %>% as.data.frame())[1,1]
num.oggs.an <- nrow(an.oggs) # Count the orthologous genes
an.oggs <- suppressMessages(
  an.oggs %>% 
    filter(am %in% (tbl(my_db, "ebseq_padj_gene_am") %>% as.data.frame())[,1],
           ln %in% (tbl(my_db, "ebseq_padj_gene_ln") %>% as.data.frame())[,1]) %>% 
    mutate(Species = "Apis and L. niger") %>% 
    left_join(tbl(my_db, "ebseq_gene_am") %>% 
                select(gene, PostFC) %>% 
                rename(am=gene), copy=T) %>% 
    rename(`Apis FC` = PostFC) %>%
    left_join(tbl(my_db, "ebseq_gene_ln") %>% 
                select(gene, PostFC) %>% 
                rename(ln=gene), copy=T) %>% 
    rename(`L. niger FC` = PostFC) %>%
    left_join(tbl(my_db, "bee_names") %>% 
                rename(am=gene), copy=T))
num.overlap.an <- nrow(an.oggs) # Count the overlaps
test2 <- overlap.hypergeometric.test(num.overlap.an, n.am, n.ln, num.oggs.an, "Apis and L. niger") # Run the hypergeometric test

# flavus and niger
fn.oggs <- make.OGGs(c("lf", "ln"))[[2]] # Get the orthologous gene list
n.lf <- (tbl(my_db, "ebseq_padj_gene_lf") %>% 
           filter(gene %in% fn.oggs$lf) %>%
           summarise(n=n()) %>% as.data.frame())[1,1] # Count the number of diff expressed genes that appear in the OGG list
n.ln <- (tbl(my_db, "ebseq_padj_gene_ln") %>% 
           filter(gene %in% fn.oggs$ln) %>% 
           summarise(n=n()) %>% as.data.frame())[1,1]
num.oggs.fn <- nrow(fn.oggs) # Count the orthologous genes
fn.oggs <- suppressMessages(
  fn.oggs %>% filter(ln %in% (tbl(my_db, "ebseq_padj_gene_ln") %>% as.data.frame())[,1],
                     lf %in% (tbl(my_db, "ebseq_padj_gene_lf") %>% as.data.frame())[,1]) %>% 
    mutate(Species = "L. flavus and L. niger") %>% 
    left_join(tbl(my_db, "ebseq_gene_lf") %>% 
                select(gene, PostFC) %>% 
                rename(lf=gene), copy=T) %>% 
    rename(`L. flavus FC` = PostFC) %>%
    left_join(tbl(my_db, "ebseq_gene_ln") %>% 
                select(gene, PostFC) %>% 
                rename(ln=gene), copy=T) %>% 
    rename(`L. niger FC` = PostFC) %>%
    left_join(tbl(my_db, "lf2am"), copy=T) %>%
    left_join(tbl(my_db, "bee_names") %>% 
                rename(am=gene), copy=T))
num.missing <- sum(is.na(fn.oggs$name))
fn.oggs$name[is.na(fn.oggs$name)] <- paste("Unknown gene", 1:num.missing)
num.overlap.fn <- nrow(fn.oggs) # Count the overlaps
test3 <- overlap.hypergeometric.test(num.overlap.fn, 
                                     n.lf, n.ln, 
                                     num.oggs.fn, 
                                     "L. flavus and L. niger") # Run the hypergeometric test


overlaps <- suppressMessages(
  data.frame(name = unique(c(af.oggs$name, an.oggs$name, fn.oggs$name)), 
             stringsAsFactors = F) %>%
    left_join(rbind(af.oggs %>% select(name, starts_with("Apis")),
                    an.oggs %>% select(name, starts_with("Apis")))) %>%
    left_join(rbind(af.oggs %>% select(name, ends_with("flavus FC")),
                    fn.oggs %>% select(name, ends_with("flavus FC")))) %>%
    left_join(rbind(an.oggs %>% select(name, ends_with("niger FC")),
                    fn.oggs %>% select(name, ends_with("niger FC")))) %>% distinct())
overlaps <- rbind(overlaps[overlaps$name == "myosin light chain alkali-like isoform X5", ],
                  overlaps[overlaps$name != "myosin light chain alkali-like isoform X5", ])
overlaps$Consistent <- "Yes"
overlaps$Consistent[apply(overlaps[,2:4],1,min,na.rm=T)<1 & apply(overlaps[,2:4],1,max,na.rm=T)>1] <- "No"
for(i in 2:4) overlaps[,i] <- format(round(log2(overlaps[,i]), 3), nsmall = 3) 
overlaps[overlaps == "    NA"] <- " "
rownames(overlaps) <- NULL

overlap.p.values <- rbind(test1, test2, test3) 
rownames(overlap.p.values) <- NULL

all.overlaps <- c(af.oggs$am, an.oggs$am, fn.oggs$am[!is.na(fn.oggs$am)]) %>% unique

Table S6: All orthologous genes that were significantly differentially expressed between pheromone treatments in more than one species. The FC columns give the Log\(_2\) fold-change in expression for each species where the focal gene was significantly differentially expressed, where positive numbers mean it was expressed at a higher level in control animals. The last column highlights genes that responded to treatment in a consistent or inconsistent direction across species. B. terrestris is omitted because neither of its differentially expressed genes were significantly affected by treatment in the other three species.

kable.table(overlaps)
name Apis FC L. flavus FC L. niger FC Consistent
myosin light chain alkali-like isoform X5 0.444 0.372 0.350 Yes
proteasome subunit beta type-5-like 0.484 -0.434 No
probable Bax inhibitor 1 0.447 -0.167 No
intracellular protein transport protein USO1 isoform X2 -0.684 0.445 No
muscle M-line assembly protein unc-89 isoform X5 -0.526 0.213 No
transitional endoplasmic reticulum ATPase TER94 0.544 -0.306 No
actin related protein 1 0.762 0.083 Yes
tubulin alpha-1 chain-like 0.773 -0.251 No
Unknown gene 1 -0.088 0.048 No
uncharacterized protein LOC100576760 isoform X2 -0.066 -0.163 Yes
myosin regulatory light chain 2 0.258 0.279 Yes
NADP-dependent malic enzyme isoform X3 0.040 -0.067 No
transketolase isoform 1 -0.248 -0.342 Yes
troponin T, skeletal muscle 0.374 0.185 Yes
uncharacterized protein LOC551958 0.511 -0.108 No
probable cytochrome P450 304a1 -0.224 0.470 No
Unknown gene 2 0.181 0.092 Yes
WD repeat-containing protein 37-like isoform X4 0.083 0.407 Yes
Unknown gene 3 -0.131 -0.211 Yes
uncharacterized protein LOC409805 isoform X3 0.444 0.415 Yes
ADP/ATP translocase 0.054 0.154 Yes
peroxidase isoformX2 0.104 0.008 Yes
neurofilament heavy polypeptide-like isoform X2 0.377 0.069 Yes
fatty acid synthase-like isoform 1 -0.926 -1.015 Yes
LOW QUALITY PROTEIN: counting factor associated protein D-like -0.294 -0.097 Yes
myophilin-like 0.226 0.216 Yes
Unknown gene 4 0.039 0.254 Yes
hexaprenyldihydroxybenzoate methyltransferase, mitochondrial-like 7.514 -0.368 No
arginine kinase isoform X2 0.441 0.141 Yes
heat shock protein cognate 4 -0.369 -0.432 Yes
tropomyosin-1-like 0.116 0.393 Yes
6-phosphogluconate dehydrogenase, decarboxylating -0.445 -0.603 Yes
transaldolase -0.044 0.034 No
superoxide dismutase 1 -0.175 -0.324 Yes
translation elongation factor 2-like isoform 1 -0.079 0.004 No
very-long-chain enoyl-CoA reductase-like -0.201 -0.431 Yes
Unknown gene 5 0.350 0.359 Yes


Table S7: The overlap between the lists of significantly differently expressed orthologous genes was significantly higher than expected for L. flavus and L. niger, suggesting that queen pheromone has conserved effects on gene expression between these two species (results based on a hypergeometric test). For the other two species pairs, the number of overlapping genes was not higher or lower than expected under the null hypothesis that queen pheromone affects a random set of genes in each species.

pander(overlap.p.values, split.cell = 40, split.table = Inf)
Species Test p
Apis and L. flavus Overlap is higher than expected: 0.1915
Apis and L. niger Overlap is higher than expected: 0.2616
L. flavus and L. niger Overlap is higher than expected: 0
most.pheromone.sensitive.genes <- function(){
  ngenes.list <- (1:5)*100 # 100 - 500
  dat <- list()
  for(i in 1: length(ngenes.list)){
    ngenes <- ngenes.list[i]
    
    # Get the top n genes from Apis, as ranked by the absolute value for the log-fold change in response to pheromone
    g1 <- tbl(my_db, "ebseq_gene_am") %>% collect() %>% 
      select(gene, PostFC) %>% 
      mutate(PostFC = log2(PostFC)) %>% left_join(tbl(my_db, "bee_names"), copy=TRUE, by = "gene") %>% 
      arrange(-abs(PostFC)) %>% head(ngenes) %>% .$name %>% unique()
    
    # Do the same for genes from non-Apis species, and get the Apis names for the top BLAST hits in the Apis genome
    g2 <- tbl(my_db, "ebseq_gene_bt") %>% 
      select(gene, PostFC) %>% 
      left_join(tbl(my_db, "bt2am") %>% 
                  rename(gene = bt) %>% 
                  select(-evalue), by = "gene") %>%
      collect() %>% mutate(PostFC = log2(PostFC)) %>% 
      arrange(-abs(PostFC)) %>% 
      rename(bt = gene, gene = am) %>% 
      left_join(tbl(my_db, "bee_names"), copy=TRUE, by = "gene") %>% 
      filter(!is.na(name)) %>% head(ngenes) %>% .$name %>% unique()
    
    g3 <- tbl(my_db, "ebseq_gene_lf") %>% 
      select(gene, PostFC) %>% 
      left_join(tbl(my_db, "lf2am") %>% 
                  rename(gene = lf) %>% 
                  select(-evalue), by = "gene") %>%
      collect() %>% mutate(PostFC = log2(PostFC)) %>% 
      arrange(-abs(PostFC)) %>% 
      rename(lf = gene, gene = am) %>% 
      left_join(tbl(my_db, "bee_names"), copy=TRUE, by = "gene") %>% 
      filter(!is.na(name)) %>% head(ngenes) %>% .$name %>% unique()
    
    g4 <-tbl(my_db, "ebseq_gene_ln") %>% 
      select(gene, PostFC) %>% 
      left_join(tbl(my_db, "ln2am") %>% 
                  rename(gene = ln) %>% 
                  select(-evalue), by = "gene") %>%
      collect() %>% mutate(PostFC = log2(PostFC)) %>% 
      arrange(-abs(PostFC)) %>% 
      rename(ln = gene, gene = am) %>% 
      left_join(tbl(my_db, "bee_names"), copy=TRUE, by = "gene") %>% 
      filter(!is.na(name)) %>% head(ngenes) %>% .$name %>% unique()
    
    # Count the number of intersections, and find gene names that appear in 3 or 4 species using the venn() function
    venn.diagram <- venn(list(am=g1, bt=g2, lf=g3, ln=g4), show.plot=FALSE) 
    three.plus <- attr(venn.diagram, "intersections")[str_count(names(attr(venn.diagram, "intersections")), ":") > 1] %>% 
      unlist %>% unname %>% unique %>% sort
    four <- attr(venn.diagram, "intersections")[str_count(names(attr(venn.diagram, "intersections")), ":") > 2] %>% 
      unlist %>% unname %>% unique %>% sort
    three <- three.plus[!(three.plus %in% four)]
    if(length(three) + length(four) > 0) dat[[i]] <- data.frame(Name = c(three, four), 
                                                                count = c(rep("x3 species", length(three)), 
                                                                          rep("4 species", length(four))), 
                                                                nGenes = ngenes, stringsAsFactors = FALSE)
  }
  dat <- do.call("rbind", dat) %>%
    arrange(count, nGenes, Name) %>%
    distinct(paste(Name, count), .keep_all = TRUE) %>%
    select(Name, count, nGenes) %>%
    mutate(count = replace(count, count == "x3 species", "3 species")) 
  
  names(dat) <- c("Name", "Appears in", "Size of gene set")
  dat
}
most.pheromone.sensitive.genes <- most.pheromone.sensitive.genes()

Table S8: List of genes that appear in the top n-most pheromone-sensitive genes for 3 or 4 species. To generate the table, we ranked genes by the absolute value of their log fold change in response to queen pheromone, then listed the gene names that appeared in 3-4 species. For non-Apis species, we found the gene names by comparison with the Apis genome by BLAST. This exercise was performed with n = 100, 200 … 500, and the third column lists the smallest n for which the gene in question appeared (for example, the gene protein takeout-like appeared for all 4 species when inspecting the top 200+ genes).

kable(most.pheromone.sensitive.genes, "html") %>%
  kable_styling() %>%
  scroll_box(height = "300px")
Name Appears in Size of gene set
protein takeout-like 4 species 200
glucose dehydrogenase [FAD, quinone] 4 species 300
histone-lysine N-methyltransferase SETMAR-like 4 species 300
serotonin receptor 4 species 500
titin-like 4 species 500
uncharacterized protein LOC102656088 4 species 500
histone-lysine N-methyltransferase SETMAR-like 3 species 200
2-oxoglutarate dehydrogenase, mitochondrial-like isoform X5 3 species 300
probable serine/threonine-protein kinase DDB_G0282963 isoform X4 3 species 300
titin-like 3 species 300
elongation of very long chain fatty acids protein 6-like 3 species 400
ligand-gated chloride channel homolog 3 precursor 3 species 400
odorant receptor Or2-like 3 species 400
putative odorant receptor 13a-like 3 species 400
serotonin receptor 3 species 400
trypsin-1 3 species 400
uncharacterized protein LOC100576902 3 species 400
uncharacterized protein LOC102655422 3 species 400
uncharacterized protein LOC102656088 3 species 400
metabotropic glutamate receptor 7 isoform X3 3 species 500
probable cytochrome P450 305a1 3 species 500
protein NPC2 homolog 3 species 500
suppressor protein SRP40-like 3 species 500
uncharacterized protein LOC100577132 3 species 500
uncharacterized protein LOC102656830 3 species 500
uncharacterized protein LOC724216 3 species 500

Most pheromone-sensitive genes are evolutionarily ancient

We defined a gene as “evolutionarily ancient” if it has an ortholog in at least one species from the other lineage (for example, we define ancient A. mellifera genes as those that have a reciprocal best BLAST hit in one or both Lasius species). Genes that were not detected by BLAST in the other lineage were defined as putatively lineage-specific (though many of them are likely to be conserved genes that we failed to identify as such, hence the word “putative”). Using a Chi-square test, we find that genes that are significantly differentially expressed in response to queen pheromone are more likely to be ancient than those that are not differentially exressed. This relationship holds for all three species for which we found differential expression, and for genes that were higher or lower in the pheromone treatment. The fact that we probably miscalssifed many genes as ancient vs lineage-specific means that the result is likely to be even stronger than suggested here.

ancient.genes.test <- function(species){   
 if(species == "am") ancient.genes <- c(make.OGGs(c("am", "lf"))[[2]]$am, 
                                        make.OGGs(c("am", "ln"))[[2]]$am) %>% unique
 if(species == "bt") ancient.genes <- c(make.OGGs(c("bt", "lf"))[[2]]$bt, 
                                        make.OGGs(c("bt", "ln"))[[2]]$bt) %>% unique
 if(species == "lf") ancient.genes <- c(make.OGGs(c("lf", "am"))[[2]]$lf, 
                                        make.OGGs(c("lf", "bt"))[[2]]$lf) %>% unique
 if(species == "ln") ancient.genes <- c(make.OGGs(c("ln", "am"))[[2]]$ln, 
                                        make.OGGs(c("ln", "bt"))[[2]]$am) %>% unique
 lab <- "Putatively bee-specific"
 if(species %in% c("lf", "ln")) lab <- "Putatively ant-specific"
 
 expression <- tbl(my_db, paste("ebseq_gene_", species, sep="")) %>% 
   select(gene, PostFC) %>% collect() %>%
   mutate(age = lab, sig = "Non-sig") %>% as.data.frame()
 expression$age[expression$gene %in% ancient.genes] <- "Evolutionarily ancient"
 expression$sig[expression$gene %in% (tbl(my_db, paste("ebseq_padj_gene_", species, sep="")) %>% 
                                        filter(PostFC < 1) %>% select(gene) %>% collect %>% .$gene)] <- "Up in QP"
 expression$sig[expression$gene %in% (tbl(my_db, paste("ebseq_padj_gene_", species, sep="")) %>% 
                                        filter(PostFC > 1) %>% select(gene) %>% collect %>% .$gene)] <- "Up in Control"
  tab <- table(expression$sig, expression$age)
  chisq.test(tab) %>% print
  percent <- paste("(", (100*tab / rowSums(tab)) %>% round(1) %>% format(nsmall=1), "%)", sep = "")
  for(i in 1:2) {for(j in 1:3) tab[j,i] <- paste(tab[j,i], percent[j + (i-1)*3])}
  tab %>% pander
}

Apis mellifera

ancient.genes.test("am") 
## 
##  Pearson's Chi-squared test
## 
## data:  tab
## X-squared = 43.581, df = 2, p-value = 3.439e-10
  Evolutionarily ancient Putatively bee-specific
Non-sig 5461 (47.4%) 6061 (52.6%)
Up in Control 150 (70.1%) 64 (29.9%)
Up in QP 54 (50.0%) 54 (50.0%)

Lasius flavus

ancient.genes.test("lf") 
## 
##  Pearson's Chi-squared test
## 
## data:  tab
## X-squared = 344.8, df = 2, p-value < 2.2e-16
  Evolutionarily ancient Putatively ant-specific
Non-sig 7167 (14.4%) 42488 (85.6%)
Up in Control 76 (41.5%) 107 (58.5%)
Up in QP 72 (67.3%) 35 (32.7%)

Lasius niger

ancient.genes.test("ln") 
## 
##  Pearson's Chi-squared test
## 
## data:  tab
## X-squared = 16.823, df = 2, p-value = 0.0002223
  Evolutionarily ancient Putatively ant-specific
Non-sig 4524 (23.0%) 15129 (77.0%)
Up in Control 30 (42.9%) 40 (57.1%)
Up in QP 19 (29.2%) 46 (70.8%)

Correlations in pheromone-sensitive gene expression across species

These tests ask if genes that are up-regulated in the queen pheromone treatment in one species are also up (or down) regulated in another. These tests used fold expression changes calculated using ebseq, after omitting the four irregular Lasius samples. The advantage of these tests is that one is not limited to the set of ‘significant’ genes, which discards a lot of information based on an arbitrary p-value threshold.

Define function to retrieve fold-change expression data (calculated with ebseq) for genes that are each other’s reciprocal best BLAST

get.fc.for.pair.species <- function(species1, species2){
  query <- 'SELECT rbb.X AS X_gene, rbb.Y AS Y_gene, ebseq_gene_X.PostFC AS X_fc, ebseq_gene_Y.PostFC AS Y_fc FROM ebseq_gene_X
             JOIN
  (SELECT Y2X.X, Y2X.Y  FROM Y2X
  JOIN X2Y
  ON Y2X.Y = X2Y.Y AND Y2X.X = X2Y.X  ) AS rbb
  ON rbb.X = ebseq_gene_X.gene
  JOIN ebseq_gene_Y
  ON rbb.Y = ebseq_gene_Y.gene'
  
  query <- str_replace_all(query, "X", species1)
  query <- str_replace_all(query, "Y", species2)
  dbGetQuery(db, query)
}

Make a table and a plot of the correlations for each pair of species

Table S9: Results of Spearman’s rank correlations, testing whether the absolute log fold difference between pheromones treatments is correlated for a given pair of species. Positive coefficients (rho) indicate that on average, orthologous genes have similar sensitivity to queen pheromones. The p-values have been corrected for multiple testing with the Benjamini-Hochberg method.

species.combinations <- t(combn(c("am", "bt", "lf", "ln"), 2))
rho <- numeric(nrow(species.combinations))
p <- numeric(nrow(species.combinations))
for(i in 1:nrow(species.combinations)){
  fc.data <- get.fc.for.pair.species(species.combinations[i, 1], 
                                     species.combinations[i,2])
  fc.data[,3:4] <- fc.data[,3:4] %>% log2 %>% abs # Log the fold changes - not that it matters for Spearman's!
  results <- suppressWarnings(with(fc.data, cor.test(fc.data[,3], 
                                                     fc.data[,4], method="spearman"))) # Spearman's correlation
  rho[i] <- results$estimate
  p[i] <- results$p.value
}

species.combinations <- data.frame(Species1 = species.combinations[,1],
                                   Species2  = species.combinations[,2],
                                   rho = rho,
                                   p = p.adjust(p, method = "BH"), # adjust these p-vals for multiple testing
                                   sig = " ", stringsAsFactors = F)

species.combinations[species.combinations == "am"] <- "Apis mellifera"
species.combinations[species.combinations == "bt"] <- "Bombus terrestris"
species.combinations[species.combinations == "lf"] <- "Lasius flavus"
species.combinations[species.combinations == "ln"] <- "Lasius niger"

species.combinations$sig[species.combinations$p < 0.05] <- "*"
species.combinations$sig[species.combinations$p < 0.01] <- "**"
species.combinations$sig[species.combinations$p < 0.0001] <- "***"
# Make a table
species.combinations %>% mutate(rho = format(round(rho, 3), nsmall = 3)) %>% pander
Species1 Species2 rho p sig
Apis mellifera Bombus terrestris 0.136 3.232e-24 ***
Apis mellifera Lasius flavus 0.100 1.478e-12 ***
Apis mellifera Lasius niger 0.077 1.853e-07 ***
Bombus terrestris Lasius flavus 0.159 3.112e-39 ***
Bombus terrestris Lasius niger 0.127 2.282e-24 ***
Lasius flavus Lasius niger 0.194 3.765e-61 ***
# Make a figure
heat.map.figure <- species.combinations %>% ggplot(aes(Species1, Species2, fill=rho)) + 
  geom_tile(colour="white", size=4) + 
  scale_fill_gradient2(name = "Corr", 
                       low = brewer.pal(9, "RdYlBu")[7], 
                       mid = "white", 
                       high = brewer.pal(9, "RdYlBu")[2]) + 
  geom_text(aes(label = paste(format(signif(rho, 2), nsmall = 2), sig)), size = 3.5) +
  theme_bw() + theme(panel.grid = element_blank(), 
                     panel.border = element_blank(), 
                     axis.ticks = element_blank(), 
                     axis.text = element_text(face = "italic"), 
                     legend.position = "none") + 
  xlab(NULL) + ylab(NULL) +
  scale_x_discrete(labels = c("Apis\nmellifera", "Bombus\nterrestris", "Lasius\nflavus"), expand = c(0,0)) + 
  scale_y_discrete(labels = c("Bombus\nterrestris", "Lasius\nflavus", "Lasius\nniger"), expand = c(0,0)) 
heat.map.figure

ggsave(heat.map.figure, file = "figures/Correlations heat map.pdf", height = 4, width=4.3)



Figure S3: Results of Spearman’s rank correlations, testing whether the fold-change in gene expression in response to queen pheromone is correlated for a given pair of species. The colour shows the correlation (Spearman’s rho), where red indicates that on average, orthologous genes are affected in the same direction by queen pheromones, and blue indicates the reverse. The stars show the degree of statistical significance after FDR correction (** p < 0.01, *** p < 0.0001).

Identifying genes that splice differently following queen pheromone treatment

Many genes showed alternative splicing in all four species, with the great majority showing between 1 and 6 isoforms.

rbind(my_db %>% tbl("isoforms_am") %>% collect %>% .$gene %>% 
        table %>% melt %>% select(value) %>% mutate(sp = "Apis mellifera"),
      my_db %>% tbl("isoforms_bt") %>% collect %>% .$gene %>% 
        table %>% melt %>% select(value) %>% mutate(sp = "Bombus terrestris"),
      my_db %>% tbl("isoforms_lf") %>% collect %>% .$gene %>% 
        table %>% melt %>% select(value) %>% mutate(sp = "Lasius niger"),
      my_db %>% tbl("isoforms_ln") %>% collect %>% .$gene %>% 
        table %>% melt %>% select(value) %>% mutate(sp = "Lasius flavus")) %>% 
  as.data.frame() %>%
  ggplot(aes(x = value, y = sp, fill = sp)) + 
  geom_joy(stat = "binline", binwidth=1) + 
  coord_cartesian(xlim=c(1,12)) + 
  scale_fill_cyclical(values = c("#4040B0", "#9090F0")) + 
  scale_x_continuous(breaks = seq(1,12,by=1)) + 
  scale_y_discrete(expand = c(0.01, 0)) + 
  theme_joy() + 
  xlab("Number of isoforms") + ylab(NULL) + 
  theme(axis.text = element_text(face = "italic"))



Figure S4: Distribution of isoform numbers per gene for each of the four species.

# Define a function to search for significantly alternatively spliced genes. We define these as genes that have at least two differentially expressed isoforms, where queen pheromone stimulates expresison of one isoform but surpresses expression of another

find.alternatively.spliced.genes <- function(species){
  
  # Write a database query with 'X' as a placeholder for the species name
  # We want to find genes in which at least two isoforms are differentially expressed in response to pheromones
  # Significant isoforms are listed in the ebseq_padj_isoform_X tables, so we count them and get the names of their genes
  query <- 'SELECT isoforms_X.gene, isoforms_X.isoform, PostFC FROM isoforms_X
JOIN
             (SELECT gene, COUNT(*) FROM ebseq_padj_isoform_X 
             JOIN isoforms_X
             ON isoforms_X.isoform = ebseq_padj_isoform_X.isoform
             GROUP BY gene
             HAVING COUNT(*)>1 ) AS multiISO
             ON multiIso.gene = isoforms_X.gene
             JOIN ebseq_padj_isoform_X 
             ON ebseq_padj_isoform_X.isoform = isoforms_X.isoform
             ORDER BY isoforms_X.gene'
  query <- str_replace_all(query, "X", species) # replace X with the species
  Splice <- dbGetQuery(db, query) # run the query

  # Find the highest and lowest fold change for the isoforms of each gene
  SpliceMin <- aggregate(Splice$PostFC, by=list(Splice$gene), FUN="min")
  SpliceMax <- aggregate(Splice$PostFC, by=list(Splice$gene), FUN="max")
  SpliceCompare <- merge(SpliceMin, SpliceMax, by = "Group.1")
  colnames(SpliceCompare) <- c("gene", "min", "max")
  
  # Define diff-spliced genes as those with both elevated and 
  # repressed isoforms, when comparing control and pheromone-treated workers
  output <- data.frame(gene = SpliceCompare$gene[SpliceCompare$min < 1 & SpliceCompare$max > 1], stringsAsFactors = F)
  
  # Add the Apis mellifera ortholog, from one-way BLAST, if it's a non-Apis species
  if(species != "am"){
    orthologs <- tbl(my_db, paste(species, "2am", sep = "")) %>% select(-evalue) %>% collect(n=Inf) %>% as.data.frame()
    names(orthologs) <- c("gene", "Amel_ortholog")
    output <- left_join(output, orthologs, by = "gene") 
    output <- left_join(output, tbl(my_db, "bee_names") %>% 
                          rename(Amel_ortholog = gene), copy=T, by = "Amel_ortholog") 
  }
  else output <- left_join(output, tbl(my_db, "bee_names"), by = "gene", copy = T)
  
  output[is.na(output)] <- " "
  
  # Remove the 'isoform X' part from the gene name, so it gives the name of the gene not the isoform
  output$name <- unlist(lapply(strsplit(output$name, split = " isoform "), function(x) x[1]))
  
  output <- left_join(output, SpliceCompare, by = "gene") 
  
  output$min <- log2(output$min) # Log2 transform the fold changes
  output$max <- log2(output$max)
  output <- output %>% arrange(-(abs(min) + max)) # Arrange by effect size
  
  if(species == "am" | species == "bt") names(output) <- c("Gene", "Name", "Lowest FC", "Highest FC")
  else names(output) <- c("Gene", "Amel ortholog", "Name", "Lowest FC", "Highest FC")
  output
}

Genes showing pheromone-induced alternative splicing in A. mellifera

Table S10: List of genes showing statistically significant pheromone-induced alternative splicing in A. mellifera. These genes were defined as those that have at least two isoforms that are differentially expressed following pheromone treatment with p < 10-5, and for which one isoform increases in expression while another decreases. The last two columns show the fold changes of the most down-regulated and most up-regulated isoforms, on a Log\(_2\) scale.

am.alt.splice <- find.alternatively.spliced.genes("am")
kable.table(am.alt.splice)
Gene Name Lowest FC Highest FC
GB44254 uncharacterized protein LOC411586 -10.2106382 7.3294705
GB55598 troponin I -8.6184698 7.4257311
GB55650 ryanodine receptor 44F -8.6521541 6.1211069
GB42000 cAMP-specific 3’,5’-cyclic phosphodiesterase, isoforms N/G -7.8461925 6.4652082
GB49567 sestrin-1-like isoformX1 -6.7384430 6.3303655
GB46113 uncharacterized protein LOC726188 -6.7215768 6.2049532
GB55237 disco-interacting protein 2 -6.4126080 5.7870758
GB44556 uncharacterized protein LOC411962 -5.3193508 6.4264182
GB50923 serine-protein kinase ATM -5.4981139 6.1549064
GB50941 phosphatidate phosphatase LPIN2-like -6.1378916 5.3694436
GB55848 DNA ligase 1-like -6.0254223 5.3645877
GB42142 nuclear hormone receptor FTZ-F1 -6.0475859 5.2543590
GB45259 zinc finger protein 91-like -5.7141149 5.4922565
GB52595 zinc finger and BTB domain-containing protein 20-like -6.0058327 5.1479879
GB55225 sushi, von Willebrand factor type A, EGF and pentraxin domain-containing protein 1 -3.5827048 7.3608415
GB55102 F-box only protein 28-like -5.6780118 5.1328776
GB42895 trichohyalin-like -6.0749616 4.6900449
GB44373 protein zyg-11 homolog B-like -2.7153166 7.8600431
GB49111 neuropathy target esterase sws -1.8617078 8.3596119
GB46271 protein BCL9 homolog -3.1471390 6.9356291
GB53431 inositol hexakisphosphate kinase 2-like -6.3417004 3.3365701
GB44336 protein couch potato-like -2.1830854 7.3541749
GB45277 multidrug resistance-associated protein 4-like -8.1135336 1.3365168
GB40263 dentin sialophosphoprotein-like -3.0597817 6.2723878
725417 uncharacterized protein LOC725417 -2.8308639 6.1603441
GB55517 uncharacterized protein LOC410000 -3.2763532 5.3768010
GB55429 CREB-regulated transcription coactivator 1-like -5.3728279 3.1844409
GB55998 beta-1,4-N-acetylgalactosaminyltransferase bre-4 -2.7284140 5.5956924
GB52604 LIM domain-binding protein 2-like -2.2872276 5.8679044
GB41734 reversion-inducing-cysteine-rich protein with kazal motifs -5.9697261 1.9393374
GB49535 calcium/calmodulin-dependent protein kinase II -1.9949124 5.8059893
GB45662 conserved oligomeric Golgi complex subunit 4-like -5.3583810 2.1410794
GB40310 uncharacterized protein LOC411575 -0.9447237 6.4575407
GB51117 rho GTPase-activating protein 18-like -0.9711563 6.3563951
GB41129 protein LMBR1L-like -5.6199019 1.4425609
GB44876 uncharacterized protein LOC100576421 -5.3652303 1.6410521
GB50244 NHL repeat-containing protein 2 -0.9371409 5.9580141
GB47138 calcium-activated potassium channel slowpoke-like -0.9035332 5.9504672
GB50099 uncharacterized abhydrolase domain-containing protein DDB_G0269086-like -1.5085077 5.0811380
GB41908 PERQ amino acid-rich with GYF domain-containing protein CG11148-like -1.0050181 5.5164280
GB52999 neurofilament heavy polypeptide-like -2.7388052 3.6790149
GB51651 putative inorganic phosphate cotransporter-like -5.4170376 0.9305746
GB50877 tyrosine-protein kinase Dnt -2.5061716 3.1568560
GB43220 transcription termination factor 2 -3.2229375 1.8337147
GB40565 ribosomal protein S6 kinase alpha-5 -2.3132702 2.6623092
GB55467 neural cell adhesion molecule L1-like -3.3341247 1.4565432
GB48034 protein numb-like, transcript variant X5 -1.0127583 3.7699557
GB55570 transmembrane protein 53-like -2.0692979 2.6556081
GB49417 PITH domain-containing protein GA19395-like -2.1836294 2.2457448
GB43282 guanine nucleotide-binding protein G(q) subunit alpha-like -2.3600303 2.0113196
GB48573 probable multidrug resistance-associated protein lethal(2)03659-like -2.1285308 1.9867141
GB50366 uncharacterized protein LOC551450 -0.8408050 1.1435481
GB46121 ubiquitin fusion degradation protein 1 homolog -0.9511837 0.9182434
GB52052 venom carboxylesterase-6-like -0.7021931 0.9102424

Genes showing pheromone-induced alternative splicing in L. flavus

Table S11: List of genes showing statistically significant pheromone-induced alternative splicing in L. flavus. The table shows the same information as Table S10.

lf.alt.splice<- find.alternatively.spliced.genes("lf")
kable.table(lf.alt.splice)
Gene Amel ortholog Name Lowest FC Highest FC
TRINITY_DN11346_c0_g1 GB49250 heme oxygenase -9.1733822 4.2807355
TRINITY_DN14030_c0_g1 XP_016769715.1 -4.5698062 6.1058670
TRINITY_DN13728_c1_g1 GB44606 AMP deaminase 2-like -5.6147192 4.2278104
TRINITY_DN13759_c0_g1 XP_016766389.1 -3.7805082 5.5650278
TRINITY_DN13897_c0_g1 GB41293 histone acetyltransferase KAT8 -4.6420034 2.6858828
TRINITY_DN14126_c1_g2 GB43039 restin homolog -1.8789713 5.3598354
TRINITY_DN12581_c0_g2 XP_016767063.1 -4.1075789 2.7973408
TRINITY_DN14084_c0_g1 XP_016772396.1 -2.4056262 4.1607373
TRINITY_DN13929_c0_g1 GB53852 paired amphipathic helix protein Sin3a -2.0878837 4.4200505
TRINITY_DN13956_c0_g1 GB54341 RNA-binding protein 33-like -1.9836823 4.5150571
TRINITY_DN13699_c0_g1 GB41835 sorting nexin-13-like -2.5195188 3.9141700
TRINITY_DN13676_c0_g1 XP_016767354.1 -3.9853775 2.2791646
TRINITY_DN13889_c0_g1 GB44338 small G protein signaling modulator 3 homolog -2.6671307 3.5553713
TRINITY_DN11861_c1_g1 GB43504 neural/ectodermal development factor IMP-L2 -2.2204311 3.4241368
TRINITY_DN14001_c0_g2 GB41033 facilitated trehalose transporter Tret1-like -3.4253663 2.1957523
TRINITY_DN12063_c0_g1 GB49936 calcium uptake protein 1 homolog, mitochondrial-like -1.9568877 3.6347798
TRINITY_DN13321_c0_g1 XP_016769905.1 -2.8397819 2.7402835
TRINITY_DN13931_c4_g1 GB47270 cytochrome P450 4C1 -2.2502914 2.8866039
TRINITY_DN12721_c1_g1 GB43391 transmembrane protein 8B-like -2.1793408 2.8228945
TRINITY_DN11401_c0_g1 GB50510 uncharacterized protein LOC409674 -2.6928098 1.9864175
TRINITY_DN10695_c0_g1 XP_016773356.1 -2.1193002 2.4882173
TRINITY_DN13698_c3_g1 GB45025 mTERF domain-containing protein 1, mitochondrial-like -1.9661074 2.5552928
TRINITY_DN13919_c0_g1 GB49593 cytosolic carboxypeptidase-like protein 5-like -1.6893918 2.7745341
TRINITY_DN14156_c10_g1 XP_016768402.1 -2.0840677 2.3753245
TRINITY_DN13974_c0_g1 XP_016768210.1 -1.5945919 2.7670315
TRINITY_DN12596_c0_g1 GB40801 thioredoxin-like protein 4A-like -1.7080464 2.3372385
TRINITY_DN13248_c0_g1 GB42981 beta-1,3-glucan-binding protein -1.6951844 2.3160927
TRINITY_DN14247_c8_g2 GB52590 fatty acid synthase-like -1.0570339 1.0113553
TRINITY_DN10832_c0_g1 GB54056 serine hydroxymethyltransferase, cytosolic -1.2534345 0.3609471
TRINITY_DN11786_c1_g1 GB51214 troponin T, skeletal muscle -0.4087698 0.8466319
TRINITY_DN13339_c0_g1 GB40735 fructose-bisphosphate aldolase-like -0.1714515 0.3993615
TRINITY_DN13721_c8_g1 XP_016772716.1 -0.2069941 0.2124566
TRINITY_DN13271_c0_g1 GB40312 choline/ethanolamine kinase-like -0.1549773 0.0102486
TRINITY_DN10322_c0_g1 XP_016769014.1 -0.1131430 0.0289235

Genes showing pheromone-induced alternative splicing in L. niger

Table S12: List of genes showing statistically significant pheromone-induced alternative splicing in L. niger. The table shows the same information as Table S10.

ln.alt.splice <- find.alternatively.spliced.genes("ln")
kable.table(ln.alt.splice)
Gene Amel ortholog Name Lowest FC Highest FC
RF55_752 GB48208 protein argonaute-2 -3.2926101 6.4472781
RF55_883 XP_016770988.1 -5.9073798 3.5987463
RF55_4195 XP_016772612.1 -5.1744722 4.3092261
RF55_412 XP_016770021.1 -3.3875926 5.9670345
RF55_2523 XP_016770619.1 -4.7649090 4.0350580
RF55_3907 XP_016771611.1 -4.4508904 3.6861314
RF55_4516 GB54906 niemann-Pick C1 protein-like -3.7980002 4.3024830
RF55_2336 GB54910 tyrosine-protein kinase Abl-like -3.2249951 4.4534584
RF55_1192 XP_016769850.1 -1.9480198 5.7297004
XLOC_016164 -5.4972688 2.1282740
RF55_3254 XP_016773300.1 -2.7312184 4.8910736
RF55_1559 XP_016768510.1 -2.9908389 4.3225630
RF55_4335 XP_016767803.1 -3.8099604 3.4311823
RF55_6516 GB40718 thioredoxin reductase 1 -3.2537489 3.9222290
RF55_11163 GB53163 transient receptor potential channel pyrexia -3.9015904 3.2568624
RF55_1926 XP_016766364.1 -1.7898846 5.3146852
RF55_9605 GB42484 aminopeptidase N-like isoformX1 -5.0263823 2.0370079
XLOC_003165 -0.6701274 6.3901363
RF55_4472 GB43953 cycle -3.9049333 3.0344073
RF55_13096 XP_016767210.1 -4.8346835 2.0905931
RF55_9014 GB55507 FYVE, RhoGEF and PH domain-containing protein 4-like -3.9205477 2.9639182
RF55_8972 XP_016771571.1 -4.8894254 1.9830903
RF55_4341 XP_392463.4 -3.2324663 3.6096634
XLOC_013280 -2.4206648 4.3918399
RF55_2163 GB55475 cullin-5 -1.9499220 4.8473456
RF55_1574 XP_016770060.1 -0.5327703 6.2375585
RF55_6406 XP_016767146.1 -2.0553009 4.6650121
RF55_1819 GB51068 arrestin homolog -2.3004627 4.3994752
RF55_2357 XP_016769793.1 -4.9713497 1.7125669
RF55_2452 XP_016767413.1 -4.9414495 1.6803943
RF55_764 XP_001121384.4 -4.4683077 2.1308271
RF55_5343 XP_016766531.1 -3.3768061 3.2009350
RF55_2401 XP_016769193.1 -3.8965864 2.6724345
RF55_6625 XP_016770656.1 -2.0711259 4.4766181
RF55_4021 XP_016767419.1 -1.8167853 4.6555595
RF55_317 XP_016769975.1 -2.7140799 3.7123571
RF55_561 GB51542 PH-interacting protein -3.3596059 2.9952497
RF55_2755 GB48836 uncharacterized protein LOC100577578 -4.5392256 1.7981131
RF55_357 -4.0137355 2.2850079
RF55_9274 XP_016767607.1 -4.1097469 2.1003576
RF55_1902 GB46211 zinc finger protein 665-like -4.2211377 1.9522150
RF55_1336 XP_016767701.1 -4.2155289 1.9317851
RF55_1520 XP_016768717.1 -2.0486448 4.0217111
RF55_2217 GB47260 zinc finger protein 598-like -1.9608779 4.1054197
RF55_6360 XP_003251881.3 -3.5776193 2.4733234
RF55_15946 XP_016767569.1 -2.3204379 3.7235457
RF55_4138 XP_016766515.1 -2.3589464 3.6642057
RF55_1328 GB41746 neogenin -2.0301217 3.8766286
RF55_6748 GB52716 NAD kinase-like, transcript variant X11 -3.4936440 2.3932969
RF55_7315 GB55434 rab GDP dissociation inhibitor beta -3.1288936 2.7150106
RF55_9900 XP_016767864.1 -3.5513206 2.2796009
RF55_1325 GB44695 lysophospholipase-like protein 1-like -4.0976819 1.6743676
RF55_9036 XP_016768958.1 -3.9412444 1.7818052
RF55_742 XP_016769412.1 -2.7605014 2.9581890
RF55_9907 GB47039 dynamin -3.9896574 1.7131009
RF55_9185 XP_016768847.1 -3.8364223 1.8598316
RF55_2976 GB42054 sodium/potassium-transporting ATPase subunit alpha -2.0568520 3.6039514
RF55_4649 GB43618 aconitate hydratase, mitochondrial-like -5.0413696 0.5716779
RF55_12355 GB42664 probable ATP-dependent RNA helicase DDX43-like -1.9943294 3.6184641
RF55_1934 GB54827 synaptotagmin 1 -5.3908347 0.1905938
RF55_360 GB46768 uncharacterized MFS-type transporter C09D4.1-like -3.2312572 2.3204411
RF55_5123 XP_016772933.1 -2.7363919 2.8109308
RF55_3009 GB53317 dentin sialophosphoprotein-like -3.7638023 1.7787767
RF55_5073 GB55540 zinc finger MYM-type protein 3-like -1.8616556 3.6633963
RF55_9319 XP_016768793.1 -1.6023217 3.8961635
RF55_952 GB42014 E3 ubiquitin-protein ligase TRIP12-like -1.6637152 3.6314244
RF55_3561 GB41659 endothelin-converting enzyme 1 -1.9116224 3.3339080
RF55_4175 GB44311 actin related protein 1 -1.4407595 3.7728266
RF55_7804 -2.5441138 2.6300085
RF55_1689 XP_016768411.1 -3.3768014 1.7465719
RF55_5052 XP_016773337.1 -2.4182694 2.6840874
RF55_457 GB40931 uncharacterized protein LOC409781 -2.3507186 2.6953986
RF55_7632 XP_016767095.1 -2.0462508 2.9941556
RF55_11518 GB41804 nardilysin -2.2810020 2.7512083
RF55_4355 XP_016771542.1 -2.4450723 2.5183903
RF55_1518 XP_016768753.1 -3.0929627 1.8614463
RF55_5804 XP_016766957.1 -2.6227377 2.2732244
RF55_4425 GB51264 glutamine-dependent NAD(+) synthetase, transcript variant X3 -2.1938416 2.6792288
RF55_5947 XP_016768497.1 -2.0359071 2.6987690
RF55_3209 GB46684 monocarboxylate transporter 3-like -2.2501560 2.4459333
RF55_4132 XP_006572145.2 -1.8924997 2.7949094
RF55_3822 XP_016769466.1 -2.5889623 2.0767884
RF55_8207 XP_016767693.1 -2.6776356 1.9612772
RF55_3129 GB53974 probable RNA helicase armi -2.4754839 2.1042263
RF55_8822 GB41970 ras-like protein 2-like -2.5012521 2.0767873
RF55_9449 GB55840 protein sidekick-1-like -1.9739288 2.4747175
RF55_583 GB41366 protein MLP1-like -2.5149738 1.9248983
RF55_5597 GB46705 muscle M-line assembly protein unc-89 -4.2010432 0.1942554
RF55_7779 GB40928 tripartite motif-containing protein 2-like -1.9058556 2.4627030
RF55_1209 XP_016766933.1 -1.8405716 2.4685968
RF55_2958 XP_016771468.1 -2.2465795 1.9449655
RF55_7227 GB45211 troponin C type I -3.4951202 0.6960651
RF55_15397 XP_016766611.1 -2.1887540 1.9674339
RF55_3792 GB42024 translation initiation factor 2 -2.3474211 1.7699710
XLOC_009000 -1.9702840 2.1399072
RF55_1494 XP_016771667.1 -1.8255253 2.2245942
RF55_2964 GB45277 multidrug resistance-associated protein 4-like -1.9410464 2.0992859
RF55_13040 XP_016771370.1 -1.7071168 2.3051344
XLOC_009717 -1.8567534 2.1300834
RF55_6105 GB40496 aftiphilin-like -1.9290288 2.0409600
RF55_2225 XP_016769102.1 -2.4576563 1.5031576
RF55_7166 GB51290 ultrabithorax -1.8574204 2.0948477
RF55_2340 GB55485 DNA methyltransferase 3 -2.2221680 1.7086023
RF55_5141 GB51219 eye-specific diacylglycerol kinase -1.5771776 2.3341264
RF55_3424 GB42681 mucin-5AC-like -1.9129112 1.9909363
RF55_335 GB42666 serine palmitoyltransferase 2-like -2.1856978 1.6894768
RF55_2921 GB40416 twist -2.1419203 1.6755463
RF55_1441 GB47599 cytoplasmic dynein 1 light intermediate chain 1 -1.3649356 2.3461757
XLOC_001241 -1.9132811 1.7758352
RF55_404 GB53011 polyphosphoinositide phosphatase -2.1273247 1.5615310
RF55_11430 XP_016769030.1 -2.0923206 1.5691347
RF55_1609 GB40975 gamma-aminobutyric acid receptor subunit beta -1.9326037 1.6691322
RF55_5498 GB55971 palmitoyltransferase ZDHHC9-like -1.8138672 1.6963432
RF55_13282 GB54319 synaptotagmin 20 -1.8203872 1.6560353
RF55_4134 XP_016771187.1 -1.6338628 1.7842745
RF55_3869 GB51413 C3 and PZP-like alpha-2-macroglobulin domain-containing protein 8-like -1.8352815 1.5643281
RF55_5507 XP_016772718.1 -1.5504913 1.7564732
RF55_3824 XP_016768669.1 -1.5248764 1.6085396
XLOC_005436 -1.7586500 1.3642664
RF55_10519 GB54446 arginine kinase -2.9654802 0.1456319
RF55_310 100576851 ornithine decarboxylase antizyme 1-like -2.1712838 0.4835235
RF55_3137 GB54056 serine hydroxymethyltransferase, cytosolic -0.5039290 0.3060241
RF55_6300 XP_016767697.1 -0.1938198 0.3975841
RF55_4024 XP_016767817.1 -0.2959092 0.2953227

There are no genes showing pheromone-sensitive splicing for B. terrestris

find.alternatively.spliced.genes("bt")  
## [1] Gene       Name       Lowest FC  Highest FC
## <0 rows> (or 0-length row.names)

There is little overlap of specific pheromone-sensitive alternatively-spliced genes

lf.alt <- lf.alt.splice$Name[lf.alt.splice$Name != " "] # Exclude genes with no A. mellifera names
ln.alt <- ln.alt.splice$Name[ln.alt.splice$Name != " "]
venn(list(Apis = am.alt.splice$Name,`L. flavus` = lf.alt,`L. niger` = ln.alt))

Gene co-expression network analysis

First, we define a series of functions for gene co-expression network analysis.

# This function uses the ComBat function from the package 'sva' to remove variance in gene expression
# that is due to colony and species, allowing us to detect variance due to queen pheromone treatment.
# The use of ComBat in this fashion follows recommendations from the author of the WGCNA package. 
remove.effects.combat <- function(expression.data){
  sampleIDs <- rownames(expression.data)
  ids <- with(treatments[match(sampleIDs, treatments$id), ], 
              data.frame(
                id = sampleIDs,
                species = species,
                treatment = treatment,
                colony = paste(species, colony, sep = "")))
  
  modcombat <- model.matrix(~as.factor(treatment), data=ids)
  shh <- capture.output(expression.data <- ComBat(dat = t(expression.data), 
                                                  batch = ids$species, 
                                                  mod = modcombat, 
                                                  par.prior = TRUE))
  shh <- capture.output(expression.data <- t(ComBat(dat = expression.data, 
                                                    batch = ids$colony, 
                                                    mod = modcombat, 
                                                    par.prior = TRUE)))
  list(expression.data, ids)
}


# Build a gene coexpresison network using WGCNA package
build.network <- function(expression.data.list){
  # Pick the soft thresholding power that gives a model fit of R^2 > 0.8 for the scale-free topology model
  soft.power <- pickSoftThreshold(expression.data.list[[1]], 
                                  RsquaredCut = 0.8, verbose = 0, powerVector = 1:30)
  # Use this power to generate a gene co-expression network, using the default settings
  network <- blockwiseModules(expression.data.list[[1]], 
                              power = soft.power$powerEstimate,
                              networkType = "signed",
                              minModuleSize = 30,
                              verbose = 0,
                              saveTOMs = T)
  list(network, expression.data.list[[2]])
}


# By default, WGCNA gives the transcriptional modules random names like 'turqoise' or 'darkred'. 
# I think it's more helpful to define the biggest module as 'Module 1', the second biggest as 'Module 2', etc
# I use the label 'Module 0' for genes that were not assigned to a module
convert.module.colors.to.names <- function(network){
  module.sizes <- table(network[[1]]$colors) %>% sort %>% rev
  module.sizes <- c(module.sizes[names(module.sizes) == "grey"], 
                    module.sizes[names(module.sizes) != "grey"])
  module.mappings <- data.frame(color = names(module.sizes), 
                                new.name = paste("Module", 
                                                 0:(length(module.sizes)-1)), stringsAsFactors = F)
  network[[1]]$colors <- module.mappings$new.name[match(network[[1]]$colors, module.mappings$color)]
  names(network[[1]]$MEs) <- gsub("ME", "", names(network[[1]]$MEs))
  names(network[[1]]$MEs) <- module.mappings$new.name[match(names(network[[1]]$MEs), 
                                                            module.mappings$color)]
  network
}


# Rearrange the data in a handy format for stats and plotting, and remove the 'Module 0', the un-assigned genes
rearrange.eigengene.data <- function(network.list){
  cbind(network.list[[2]], network.list[[1]]$MEs) %>% 
    gather(Module, Eigengene, starts_with("Module")) %>% 
    filter(Module != "Module 0") %>%
    rename(Species = species, Treatment = treatment) %>% 
    arrange(Species, Treatment, colony, Module)
} 


# Run a model selection analysis on each module. The full linear model has eigengene as the response variable, and treatment, species and treatment:species as predictors. We rank the 5 possible models using their AIC scores, and test which provides the best fit to the data (the 'delta' and 'weight' parameters reveal the difference in explantory power)
run.stats <- function(dat){
  
  do.one.module <- function(module, dat){
    options(na.action = "na.fail") # need to set this option when running dredge()
    full.model <- lm(Eigengene ~ Treatment * Species, 
                     data = dat[dat$Module == paste("Module", module), ])
    output <- suppressMessages(dredge(full.model)) # compare full model and the four possible simpler models
    options(na.action = "na.omit") # set it back to default
    cbind(Module = module, output %>% as.data.frame()) # Add the module name to the results
  }
  
  stats <- do.call("rbind", # Run model selection on every module
                   lapply(1:length(unique(eigen.data$Module)), do.one.module, eigen.data))

  stats[,names(stats) %in% c("logLik", "AICc", "delta", "weight")] <- 
    format(round(stats[,names(stats) %in% c("logLik", "AICc", "delta", "weight")], 2), nsmall = 2) # rounding
  rownames(stats) <- NULL
  stats <- stats[,-2] # Remove the intercept column
  stats$Module[duplicated(stats$Module)] <- " "
  model <- rep("Null model")
  model[stats$Species == "+"] <- "~ Species"
  model[stats$Treatment == "+"] <- "~ Treatment"
  model[stats$Species == "+" & stats$Treatment == "+"] <- "~ Species + Treatment"
    model[stats$`Species:Treatment` == "+"] <- "~ Species x Treatment"
  model[is.na(model)] <- "Null model"
  stats <- with(stats, data.frame(Module, Model = model, 
                                  stats[,names(stats) %in% c("logLik", "AICc", "delta", "weight")]))
  stats
}

Make the gene co-expression network, using the set of orthologous genes for all 4 species

# The 4 bad samples get removed, then we find the orthologous genes, the data are scaled with ComBat, and then we build the network using the lowest soft-thresholding power that gives at least R^2 > 0.8 model fit
OGGs <- make.OGGs(c("am", "bt", "ln", "lf"), bad.samples = bad.samples)
network <- OGGs[[1]] %>%
  remove.effects.combat() %>% 
  build.network() %>%
  convert.module.colors.to.names()
eigen.data <- network %>% rearrange.eigengene.data

Simple statistics about the network

Here is the number of orthologous genes that form the network:

length(network[[1]]$colors)
## [1] 3465

Here is the number and size of modules in the network - module 0 refers to the unassigned genes.

table(network[[1]]$colors) %>% pander
Table continues below
Module 0 Module 1 Module 2 Module 3 Module 4 Module 5 Module 6
107 1639 543 346 288 160 154
Module 7 Module 8 Module 9
150 40 38

Make a plot of the module eigengenes

# Make a plot of the module eigengenes, split by species, module and treatment
treatments.network.plot <- function(dat){ 
  dat %>% mutate(Treatment = replace(as.character(Treatment), Treatment == "QP", "Queen\npheromone")) %>%
    ggplot(aes(Species, Eigengene, fill = Treatment)) + 
    geom_hline(yintercept = 0, linetype=2) + 
    geom_boxplot() + 
    facet_wrap(~Module) + 
    xlab(NULL) + 
    scale_x_discrete(labels = c("Apis\nmellifera", "Bombus\nterrestris", "Lasius\nflavus", "Lasius\nniger")) +
    scale_fill_brewer(name = " ", palette = "Set3", direction = -1) + 
    theme_bw() + 
    theme(strip.background = element_blank(), 
          axis.text.x = element_text(face = "italic"), 
          panel.border = element_rect(size=0.7), 
          legend.position = "top") 
}

eigen.data %>% treatments.network.plot()

ggsave(eigen.data %>% treatments.network.plot(), 
       file = "figures/Module eigengenes.pdf", height = 6.6, width = 8)



Figure 4: The figure shows the distribution of module eigengenes for each combination of module, species, and queen pheromone (QP) treatment. Positive values mean that the focal group has higher eigengenes, which derived from the relative expression levels of a module of genes, than the average.

Run model selection analysis to test for treatment and species effects on eigengenes

Table S13: Model selection analysis, using AICc (corrected Akaike Information Criterion) to rank all possible models of the module eigengene data shown in Figure S5. The models are listed from best to worst for each module. The ‘delta’ column gives the difference in AICc scores between the focal model and the top model in the set, where delta > 2 is considered to be a significant improvement in model fit. The column ‘weight’ gives Akaike weights, which can be interpreted as probabilities that the focal model is the top model in the set, given the data.

run.stats(eigen.data) %>% kable.table()
Module Model logLik AICc delta weight
1 ~ Treatment 17.71 -28.74 0.00 0.59
Null model 16.10 -27.87 0.87 0.38
~ Species + Treatment 17.72 -20.81 7.93 0.01
~ Species 16.10 -20.39 8.35 0.01
~ Species x Treatment 20.71 -17.22 11.52 0.00
2 ~ Treatment 17.28 -27.88 0.00 0.49
Null model 16.10 -27.87 0.01 0.49
~ Species 16.10 -20.39 7.49 0.01
~ Species + Treatment 17.29 -19.95 7.93 0.01
~ Species x Treatment 19.39 -14.57 13.31 0.00
3 Null model 16.10 -27.87 0.00 0.50
~ Treatment 17.24 -27.79 0.08 0.48
~ Species 16.11 -20.39 7.47 0.01
~ Species + Treatment 17.24 -19.85 8.02 0.01
~ Species x Treatment 21.01 -17.82 10.05 0.00
4 ~ Treatment 26.92 -47.15 0.00 0.92
~ Species x Treatment 33.05 -41.89 5.27 0.07
~ Species + Treatment 26.92 -39.22 7.93 0.02
Null model 16.10 -27.87 19.28 0.00
~ Species 16.11 -20.40 26.75 0.00
5 Null model 16.10 -27.87 0.00 0.60
~ Treatment 16.77 -26.86 1.01 0.37
~ Species 16.10 -20.39 7.48 0.01
~ Species x Treatment 21.77 -19.33 8.53 0.01
~ Species + Treatment 16.78 -18.93 8.94 0.01
6 Null model 16.10 -27.87 0.00 0.70
~ Treatment 16.13 -25.57 2.30 0.22
~ Species x Treatment 23.61 -23.00 4.86 0.06
~ Species 16.11 -20.40 7.47 0.02
~ Species + Treatment 16.13 -17.64 10.23 0.00
7 Null model 16.10 -27.87 0.00 0.74
~ Treatment 16.17 -25.65 2.22 0.24
~ Species 16.11 -20.39 7.48 0.02
~ Species + Treatment 16.17 -17.72 10.15 0.00
~ Species x Treatment 16.40 -8.59 19.27 0.00
8 Null model 16.10 -27.87 0.00 0.68
~ Treatment 16.44 -26.20 1.67 0.29
~ Species 16.28 -20.75 7.12 0.02
~ Species + Treatment 16.63 -18.64 9.23 0.01
~ Species x Treatment 17.98 -11.75 16.12 0.00
9 ~ Treatment 18.42 -30.15 0.00 0.74
Null model 16.10 -27.87 2.29 0.24
~ Species + Treatment 18.42 -22.22 7.93 0.01
~ Species 16.11 -20.39 9.76 0.01
~ Species x Treatment 19.58 -14.96 15.19 0.00

Plot the correlations between all modules and the pheromone treatment

meta.module.plot <- function(network){
 
  MET <- network[[1]]$MEs 
  MET <- data.frame(QP = (network[[2]]$treatment %>% as.numeric())-1, MET) %>% dplyr::select(-Module.0)
  names(MET) <- gsub("[.]", " ", names(MET))
  cluster <- (1 - cor(MET)) %>% as.dist() %>% hclust()
  ordering <- cluster$labels[cluster$order]
  heat.map.data <- cor(MET) %>% melt %>% 
    mutate(Var1 = factor(Var1, levels = ordering),
           Var2 = factor(Var2, levels = ordering)) %>% 
    rename(Corr = value)
  heat.map <- heat.map.data %>% ggplot(aes(Var1, Var2, fill = Corr)) + geom_tile() + 
    scale_fill_gradient2(low = brewer.pal(9, "RdBu")[8], 
                         mid = "white", 
                         high = brewer.pal(9, "RdBu")[2]) + 
    xlab(NULL) + ylab(NULL) + 
    theme_bw() + 
    theme(panel.border = element_blank(), 
          panel.grid = element_blank()) + 
    scale_x_discrete(expand = c(0,0)) + 
    scale_y_discrete(expand = c(0,0))
 
  dendrogram <- ggdendrogram(cluster) + theme(axis.text.x = element_blank(), axis.text.y = element_blank())
  
  p1 <- grid.arrange(dendrogram, heat.map)
  invisible(p1)
}

meta.plot <- meta.module.plot(network)

ggsave(meta.plot, file = "figures/meta_module_heat_map.pdf", width = 5, height = 7.3, units = "in")
meta.plot
## TableGrob (2 x 1) "arrange": 2 grobs
##   z     cells    name           grob
## 1 1 (1-1,1-1) arrange gtable[layout]
## 2 2 (2-2,1-1) arrange gtable[layout]



Figure S5: Dendrogram and heat map showing the correlations among module eigengene values and the queen pheromone treatment (QP; coded as zero and 1 for the control and treatment respectively). Modules with red colour, or which are close on the dendrogram, show more correlated expression. The queen pheromone treatment was correlated with Module 5, but was relatively uncorrelated with the other modules.

Table S13: Results of Spearman’s rank correlations testing for a relationship between the effect of queen pheromone on gene expression, and the connectedness of the gene. Negative values of Spearman’s Rho mean that highly pheromone-sensitive genes tend to have lower connectedness.

load("blockwiseTOM-block.1.RData") # Load the TOM from the network analysis - can be used to find connectedness for each ortholog

# Get the phermonone sensitivity value for each of the OGGs, and line it up with the connectedness data
suppressMessages(dd <- OGGs[[2]] %>% left_join(tbl(my_db, "ebseq_gene_am") %>% select(gene, PostFC) %>% rename(am=gene), copy=T) %>% rename(am_FC = PostFC) %>%
  left_join(tbl(my_db, "ebseq_gene_bt") %>% select(gene, PostFC) %>% 
              rename(bt=gene), copy=T) %>% rename(bt_FC = PostFC) %>%
  left_join(tbl(my_db, "ebseq_gene_lf") %>% select(gene, PostFC) %>% 
              rename(lf=gene), copy=T) %>% rename(lf_FC = PostFC) %>%
  left_join(tbl(my_db, "ebseq_gene_ln") %>% select(gene, PostFC) %>% 
              rename(ln=gene), copy=T) %>% rename(ln_FC = PostFC) %>%
  mutate(k = colSums(as.matrix(TOM))))

do.spearman <- function(dd, species, name){ # run spearman on each species
  test <- cor.test(dd$k, dd[, names(dd) == species] %>% log2 %>% abs, method = "spearman")  # Note that we convert the fold-change in expression with abs(log2(x)), to get pheromone sensitivity
  with(test, data.frame(Species = name, rho = estimate, p = p.value, row.names = NULL))
}

suppressWarnings(results <- rbind(do.spearman(dd, "am_FC", "Apis mellifera"),
                                  do.spearman(dd, "bt_FC", "Bombus terrestris"),
                                  do.spearman(dd, "lf_FC", "Lasius flavus"),
                                  do.spearman(dd, "ln_FC", "Lasius niger")))
rownames(results) <- NULL
pander(results)
Species rho p
Apis mellifera -0.2463 4.834e-49
Bombus terrestris -0.2988 2.076e-72
Lasius flavus -0.4151 1.854e-144
Lasius niger -0.3159 4.677e-81

Characteristics of pheromone-sensitive genes in Apis

In this section, we search for correlates of the absolute Log_2 fold change in response to pheromone (where positive values denote genes whose expression differs strongly between the control and pheromone treatment). This section makes use of data kindly provided by Soojin Yi and Brendan Hunt.

The data on queen and worker-specific gene expression come from Grozinger et al. 2007. We found that pheromone-sensitive genes tend to be over-expressed by queens relative to sterile workers. However, genes that are over-expressed by fertile workers relative to sterile workers did not tend to be more (or less) pheromone-sensitive.

The methylation level (i.e. % methylated cytosines) data come from Galbraith et al. 2016 (provided by Soojin Yi). We found a negative correlation between methylation and pheromone-sensitivity, suggesting that pheromone-sensitive genes are hypomethylated.

The CpG O/E values were calculated for the latest A. mellifera genome annotation. We found a positive correlation between CpG O/E and pheromone-sensitivity. High CpG is associated with lower rate of DNA methylation, again suggesting that pheromone-sensitive genes are hypomethylated.

The estimates of \(\gamma\), a measure of positive and negative selection similar to dN/dS, come from Harpur et al. 2014 PNAS. There was a significant positive correlation between \(\gamma\) and sensitivity to queen pheromone, suggesting that highly pheromone-sensitive genes tend to be positively selected.

The Codon adaptation index was calculated by Brendan Hunt. A high codon adaptation index denotes high codon usage bias, i.e. where certain synonymous codons are more common than others. Pheromone-sensitive genes showed low codon usage bias.

Lastly, ‘expression level’ refers to the average expression of each gene, expressed as TPM (transcripts per million) as measured by the software RSEM in the present study. Highly expressed genes tended to be less pheromone-sensitive.

# import and clean up the data provided by Brendan Hunt
hunt.data <- read.delim("data/apis_gene_comparisons/Amel_AllData_012709.txt", 
                        header=T, stringsAsFactors = FALSE) %>% 
  mutate(log2RW.SW = log2(RW_bagel / SW_bagel))        # calculate log fold difference in gene expression between fertile and sterile workers
entrez.tbl <- read.delim("data/apis_gene_comparisons/am.gene_info.txt", stringsAsFactors = FALSE)[,c(2,5,6)] # import table of gene names (Entrez, old Beebase, and new Beebase)
names(entrez.tbl) <- c("entrez.id", "beebase1", "beebase2")
hunt.data <- hunt.data %>% 
  dplyr::select(ID, log2Q.SW, log2RW.SW, CAI, cpgOE) %>% # get gene ID and the relevant data
  rename(beebase1 = ID) %>%                              # merge based on beebase IDs
  left_join(entrez.tbl, by = "beebase1") %>% 
  filter(!is.na(beebase2) & beebase2 != "-") %>% 
  mutate(beebase2 = gsub("BEEBASE:", "", beebase2)) %>% 
  rename(gene = beebase2) %>% 
  dplyr::select(gene, log2Q.SW, log2RW.SW, CAI, cpgOE)
hunt.data <- left_join(tbl(my_db, "ebseq_gene_am") %>%       # merge Hunt's data with our phermone sensitivity data
                         dplyr::select(gene, PostFC) %>% collect(), hunt.data, by = "gene") %>% 
  left_join(tbl(my_db, "bee_names") %>% collect, by = "gene")  # also add the gene names 

# Import methylation data provided by Soojin Yi and Xin Wu (from Galbraith et al PNAS)
methylation <- read.csv("data/apis_gene_comparisons/apis_gene_methyl_CG_OE.csv", stringsAsFactors = FALSE)
methylation <- tbl(my_db, "ebseq_gene_am") %>% collect %>% left_join(methylation, by = "gene") %>%
  filter(!is.na(Gene_body_methylation)) %>%
  left_join(tbl(my_db, "bee_names") %>% collect(), by = "gene") %>% distinct(gene, .keep_all = T)

# Import gamma data from Harpur et al PNAS
gamma_am <- tbl(my_db, "ebseq_gene_am") %>% collect() %>%
  left_join(read.table("data/apis_gene_comparisons/harpur_etal_gamma.txt", header=TRUE, stringsAsFactors=FALSE) %>% rename(gene = Gene), by = "gene") %>%
  filter(!is.na(gamma)) %>%
  dplyr::select(gene, PostFC, gamma) %>%
  mutate(PostFC = log2(PostFC)) %>% left_join(tbl(my_db, "bee_names"), copy=TRUE, by = "gene") %>%
  arrange(-abs(PostFC))


merged <- hunt.data %>% dplyr::select(gene, PostFC, log2Q.SW, log2RW.SW, CAI) %>% 
  left_join(methylation %>% dplyr::select(gene, CG_OE, Gene_body_methylation), by = "gene") %>% # merge in methylation data provided by Soojin Yi
  left_join(gamma_am %>% dplyr::select(gene, gamma), by = "gene") %>%                         # merge in gamma data from Harpur et al
  left_join(data.frame(gene = tbl(my_db, "rsem_am") %>% 
                         dplyr::select(gene) %>% collect(),  # calculate overall expression level from our own data
                       expression.level = (tbl(my_db, "rsem_am") %>% 
                                             dplyr::select(-gene) %>% 
                                             collect %>% rowSums())), by = "gene") %>% 
  left_join(dd %>% dplyr::select(am, k) %>% rename(gene=am), by = "gene") %>%
  dplyr::select(-gene) %>% 
  mutate(CG_OE = -log2(CG_OE),                         # log2 CpG O/E ratio - change the sign, so that high values mean high methylation
         expression.level = log10(expression.level),   # log10 the expression level
         PostFC = abs(log2(PostFC))) %>%               # absolute log2 fold-change in response to pheromones (i.e. 'pheromone sensitivity' score)
  as.data.frame() 

m.rename <- function(merged, col, new) {names(merged)[names(merged) == col] <- new; merged}
merged <- merged %>% m.rename("PostFC", "Pheromone sensitivity\n(absolute log fold)")   # re-label all the variables nicely
merged <- merged %>% m.rename("log2Q.SW", "Upregulation in queens\n(log fold)")
merged <- merged %>% m.rename("log2RW.SW", "Upregulation in fertile\nworkers (log fold)")
merged <- merged %>% m.rename("CAI", "Codon usage bias\n(CAI)")
merged <- merged %>% m.rename("CG_OE", "DNA methylation\n(CpG depletion)")
merged <- merged %>% m.rename("Gene_body_methylation", "DNA methylation\n(BiS-seq)")
merged <- merged %>% m.rename("gamma", "Positive selection\n(Gamma)")
merged <- merged %>% m.rename("expression.level", "Log Expression level")
merged <- merged %>% m.rename("k", "Connectivity in the\ntranscriptome")

reorder_cormat <- function(cormat){ # reorder a correlation matrix using hierarchical clustering
  dd <- as.dist((1-cormat)/2)
  hc <- hclust(dd)
  cormat[hc$order, hc$order]}

cormat <- reorder_cormat(cor(merged, use = 'pairwise.complete.obs'))
cormat[upper.tri(cormat)] <- NA
diag(cormat) <- NA

cor.matrix <-  (melt(cormat) %>% filter(!is.na(value)))[,1:2] %>% mutate(cor=0,p=0) 
for(i in 1:nrow(cor.matrix)) cor.matrix[i, 3:4] <- cor.test(merged[, names(merged) == cor.matrix$Var1[i]], merged[, names(merged) == cor.matrix$Var2[i]])[c(4,3)] %>% unlist
cor.matrix$p <- p.adjust(cor.matrix$p, method = "BH") # apply B-H p value correction
cor.matrix$sig <- ""
cor.matrix$sig[cor.matrix$p < 0.05] <- "*"   
cor.matrix$sig[cor.matrix$p < 0.001] <- "**"  
cor.matrix$sig[cor.matrix$p < 0.0001] <- "***"   
cor.matrix$label <- paste(format(round(cor.matrix$cor,2), nSmall =2), cor.matrix$sig)
correlation.plot <- cor.matrix %>% 
  ggplot(aes(Var1, Var2, fill=cor)) + 
  geom_tile(colour="grey10",alpha=0.7) + 
  scale_fill_gradient2(name = "Corr", 
                       low = brewer.pal(9, "RdYlBu")[7], 
                       mid = "white", 
                       high = brewer.pal(9, "RdYlBu")[2]) +
  geom_text(aes(label = label), colour = "grey25", size = 3.5) + 
  xlab(NULL) + ylab(NULL) +
  scale_x_discrete(expand=c(0,0)) + scale_y_discrete(expand=c(0, 0)) + 
  theme_minimal() + theme(axis.text.x = element_text(angle = 45, hjust = 1, face = c("bold", rep("plain", 5), "bold", "plain")), 
                          axis.text.y = element_text(face = c("plain", "bold", rep("plain", 5), "bold")), 
                          panel.grid = element_blank(), 
                          legend.position = "none") 
ggsave(correlation.plot, file = "figures/correlation_plot.pdf", width =8, height = 8)
correlation.plot



Figure 5: Correlations across genes between various parameters, for Apis mellifera. ‘Pheromone sensitivity’ was calculated as the absolute value of the Log\(_2\) fold difference in expression between pheromone treatment and the control. The Log FC (fold change) data come from Grozinger et al. 2007 (Mol. Ecol.), and positive values denote genes that have higher expression in queens or fertile workers, relative to sterile workers. Codon usage bias was estimated by the codon adaptation index: high values indicate bias for particular synonymous codons. DNA methylation rate was estimated either by the frequency of CpGs (i.e. -log CpG O/E ratio), or from bisulphite sequencing (BiS-seq). The parameter gamma (\(\gamma\)) describes the form of selection, where positive values denote positive selection, and negative values purifying selection. Lastly, the expression level was calculated from our own dataset as the log transcripts per million, averaged across our 6 Apis libraries.

Contrasting our Lasius data with results from Morandin et al. 2016

Morandin et al. 2016 (Genome Biology 17:43) studied whole transcriptomes from queens and workers in 16 diverse ant species, including two other species from the genus Lasius. Using BLAST, they grouped genes into OGGs (orthologous gene groups), and built a co-expression network using all the OGGs that were common to all 16 species (similar to the present study). Their analysis yielded 36 modules, of which many showed significant queen-worker differences in their module eigengenes. Here, we want to test whether these queen- and worker-like modules significantly overlap with the pheromone-sensitive modules in the present study.

To do this, we used BLAST to identify orthologous gens in L. niger and L. flavus that belong to one of Morandin et al.’s OGGs. We then tested for significantly-greater-than-random overlap between Morandin et al’s modules, and our own study’s modules, using hypergeometric tests.

Of all the possible module pairs, we found 6 pairs that overlapped significantly more than expected (FDR-corrected). One of these pairs included our highly pheromone-sensitive module, Module 4, which overlapped with the caste-biased Module 13 from Morandin et al. The intersecting genes include protein take-out like, a NAD kinase 2, a serine protease, and histone H2A-like.

Table S14: A list of the six module pairs, from Morandin et al. 2016 and the present study, which had significantly more genes in common than expected by chance. The p-values were calculated by running hypergeometric tests on all possible pairs of modules from the two studies, and then adjusting all the p-values using the Benjamini-Hochberg procedure.

morandin.orthology <- read.csv("data/morandin_comparison_data/Morandin to Holman orthology.csv", stringsAsFactors = FALSE)
morandin.module.membership <- read.csv("data/morandin_comparison_data/Morandin module membership.csv", stringsAsFactors = FALSE)
morandin.module.caste.bias <- read.csv("data/morandin_comparison_data/Morandin module caste bias.csv", stringsAsFactors = FALSE)
# Create list of all the L. niger & L. flavus genes are are part of
# the Orthologous Gene Groups (OGGs) from Morandin et al.
# Here are the 3634 genes for which we have 1-to-1 orthologs in all 18 species:
morandin.oggs <- make.OGGs(c("ln", "lf"))[[2]] %>% 
  left_join(morandin.orthology, by = "ln") %>%
  filter(!is.na(morandin.ogg)) %>% 
  left_join(morandin.module.membership, by = "morandin.ogg") %>%
  left_join(tbl(my_db, "ln2am") %>% 
              left_join(tbl(my_db, "bee_names"), by = c("am" = "gene")) %>%
              filter(!is.na(name)) %>% select(ln, name, am) %>% 
              rename(apis.name = name) %>% collect(n=Inf), by = "ln") %>%
  left_join(morandin.module.caste.bias, by = "module") %>%
  rename(morandin.module = module) %>%
  left_join(data.frame(ln = OGGs[[2]]$ln, 
                       holman.module = network[[1]]$colors, 
                       stringsAsFactors = F), by = "ln") %>%
  left_join(tbl(my_db, "ebseq_gene_ln") %>% 
              select(gene, PostFC) %>% collect(n=Inf) %>% rename(ln = gene), by = "ln") %>%
  rename(FC.pheromone = PostFC)
overlaps <- table(morandin.oggs$morandin.module, 
                  morandin.oggs$holman.module) %>% 
  melt() %>% rename(morandin.module = Var1, 
                    holman.module = Var2, 
                    overlaps = value) %>%
  filter(holman.module != "Module 0") %>%
  left_join(table(morandin.oggs$morandin.module) %>% 
              melt() %>% rename(mor.mod.size = value), 
            by = c("morandin.module" = "Var1")) %>% 
  left_join(table(morandin.oggs$holman.module) %>% melt() %>% 
              rename(hol.mod.size = value), by = c("holman.module" = "Var1"))

# List all the Morandin et al. modules that significantly overlap with our own modules
overlaps <- data.frame(
  overlaps, 
  do.call("rbind", 
          lapply(1:nrow(overlaps), 
                 function(i) with(overlaps, 
                                  overlap.hypergeometric.test(
                                    overlaps[i], 
                                    mor.mod.size[i], 
                                    hol.mod.size[i], 
                                    nrow(morandin.oggs), 
                                    species = "xx"))))[,2:3]) %>% 
  filter(Test == "Overlap is higher than expected:") %>% 
  arrange(p) %>% select(-Test) %>% 
  left_join(morandin.oggs %>% 
              select(morandin.module, caste.bias) %>% 
              distinct(), by = "morandin.module") %>% 
  mutate(p = p.adjust(p, method = "BH"),
         morandin.module = paste("Module", morandin.module)) %>%
  filter(p < 0.05) 
names(overlaps) <- c("Morandin module", "Holman module", "n overlapping genes", "Size of Morandin module", "Size of Holman module", "p-value", "Caste bias of Morandin module")
overlaps %>% 
  pander(split.cell = 40, split.table = Inf)
Morandin module Holman module n overlapping genes Size of Morandin module Size of Holman module p-value Caste bias of Morandin module
Module 32 Module 2 20 39 363 8.886e-09 Worker-biased
Module 31 Module 1 69 161 969 0.0002602 Queen-biased
Module 26 Module 8 5 49 24 0.0005457 Worker-biased
Module 32 Module 8 4 39 24 0.003328 Worker-biased
Module 13 Module 4 10 61 177 0.01554 Queen-biased
Module 10 Module 3 10 77 150 0.02318 Worker-biased

A list of the genes (OGGs) that appear in the present study’s Module 4 (which is pheromone-sensitive), and also in Morandin et al.’s Module 13 (which is caste-biased).

morandin.oggs %>% 
  filter(morandin.module == 13, holman.module == "Module 4") %>% 
  .$apis.name
##  [1] "tumor suppressor candidate 3-like"                      
##  [2] "methyltransferase-like isoform X3"                      
##  [3] "uncharacterized protein LOC726417"                      
##  [4] "uncharacterized protein LOC100576236 isoform X1"        
##  [5] "NAD kinase 2, mitochondrial-like"                       
##  [6] "histone H2A-like"                                       
##  [7] "protein takeout-like"                                   
##  [8] "uncharacterized protein LOC551133 isoform X2"           
##  [9] "xenotropic and polytropic retrovirus receptor 1 homolog"
## [10] "putative serine protease K12H4.7-like isoform X2"

KEGG and GO enrichment for differentially expressed genes

First, define some functions we will need. See also the R script “Script to set up for GO analyses.R”, which was used to make the object gene_set_collection.RData, following instructions for making a GO annotation for a non-model organism at http://bioconductor.org/packages/2.11/bioc/vignettes/GOstats/inst/doc/GOstatsForUnsupportedOrganisms.pdf.

There are only two differentially expressed genes for B. terrestris, so it is only meaningful to test for enriched GO/KEGG terms in the other three species.

GO.and.KEGG.enrichment <- function(enriched.genes, gene.universe, kable = TRUE, keep.all = FALSE){
  
  p <- 0.05
  neatness <- function(x, dp) format(round(x, dp), nsmall = 3)
  if(keep.all) p <- 1
  GO.enrichment <- function(enriched.genes, gene.universe, ontology){
    
    params <- GSEAGOHyperGParams(
      name = "Luke's Params",
      geneSetCollection = gene_set_collection, # custom GO annotations 
      geneIds = enriched.genes,
      universeGeneIds = gene.universe,
      ontology = ontology, # Can be BP, MF, or CC
      pvalueCutoff = p,
      conditional = TRUE, # Do the test conditional on the GO structure
      testDirection = "over") # Look for over-represented GO terms, not under
    
    output <- hyperGTest(params) %>%
      summary() %>% 
      dplyr::mutate(Pvalue = neatness(Pvalue, 5),
                    OddsRatio = neatness(OddsRatio, 3),
                    ExpCount = neatness(ExpCount, 3)) 
    names(output)[1] <- "ID"
    type <- "Biological process"
    if(ontology == "MF") type <- "Molecular function"
    if(ontology == "CC") type <- "Cellular component"
    if(nrow(output)==0) return(NULL)
    data.frame(Test_type = paste("GO", type, sep = ": "), output)
  }
  
  kegg.enrichment <- function(enriched.genes, gene.universe){
    
    params <- GSEAKEGGHyperGParams(
      name = "Luke's Params",
      geneSetCollection = gene_set_collection_kegg, # custom KEGG annotations 
      geneIds = enriched.genes,
      universeGeneIds = gene.universe,
      pvalueCutoff = p,
      testDirection = "over") # Look for over-represented KEGG terms, not under
    
    output <- hyperGTest(params) %>% 
      summary() %>% 
      dplyr::mutate(Pvalue = neatness(Pvalue, 5),
                    OddsRatio = neatness(OddsRatio, 3),
                    ExpCount = neatness(ExpCount, 3),
                    KEGGID = paste("KEGG", KEGGID, sep = ":")) %>%
      rename(ID = KEGGID)
    data.frame(Test_type = "KEGG", output)
  }
  
  output <- rbind(kegg.enrichment(enriched.genes, gene.universe), 
                  GO.enrichment(enriched.genes, gene.universe, "BP"),
                  GO.enrichment(enriched.genes, gene.universe, "MF"),
                  GO.enrichment(enriched.genes, gene.universe, "CC")) 
  if(!kable) return(output)
  output %>% kable.table()
}

# Find the names for the genes in a given module
genes.in.module <- function(module.number){
  colnames(OGGs[[1]])[network[[1]]$colors == paste("Module", module.number)]
}

# Get the gene names, and sensitivity to pheromone, for genes in a certain module
inspect.module.genes <- function(module){
  gene.names <- tbl(my_db, "bee_names") %>% as.data.frame()
  gene.names <- gene.names[gene.names$gene %in% genes.in.module(module), ]
  gene.names$k <- colSums(as.matrix(TOM)[network[[1]]$colors == paste("Module", module), 
                                        network[[1]]$colors == paste("Module", module)])
  gene.names <- gene.names %>% arrange(-k)
  
  am <- tbl(my_db, "ebseq_gene_am") %>% as.data.frame()
  gene.names$am_fc <- am$PostFC[match(gene.names$gene, am$gene)]
  bt <- tbl(my_db, "ebseq_gene_bt") %>% rename(bt = gene) %>% 
    left_join(tbl(my_db, "bt2am")) %>% as.data.frame()
  gene.names$bt_fc <- bt$PostFC[match(gene.names$gene, bt$am)]
  lf <- tbl(my_db, "ebseq_gene_lf") %>% rename(lf = gene) %>% 
    left_join(tbl(my_db, "lf2am")) %>% as.data.frame()
  gene.names$lf_fc <- lf$PostFC[match(gene.names$gene, lf$am)]
  ln <- tbl(my_db, "ebseq_gene_ln") %>% rename(ln = gene) %>% 
    left_join(tbl(my_db, "ln2am")) %>% as.data.frame()
  gene.names$ln_fc <- ln$PostFC[match(gene.names$gene, ln$am)]
  row.names(gene.names) <- NULL
  gene.names
}

# Load the gene set collection object needed for the GO tests
load("data/gene_set_collection.RData")

# Load the gene set collection object needed for the KEGG tests
load("data/gene_set_collection_kegg.RData")

KEGG and GO enrichment for differentially expressed genes in A. mellifera

Table S15: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the control group in A. mellifera. The gene universe was defined as all A. mellifera genes measured in this study.

gene.universe.apis <- (tbl(my_db, "rsem_am") %>% 
                         as.data.frame())$gene
up.in.control.apis <- (apis.de %>% filter(`Log2 FC` > 0) %>% as.data.frame())$Gene
suppressMessages(GO.and.KEGG.enrichment(up.in.control.apis, gene.universe.apis))
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:03010 0.00000 24.523 6.252 53 121 Ribosome
KEGG KEGG:03050 0.00011 5.865 2.015 9 39 Proteasome
KEGG KEGG:04145 0.01426 2.787 3.255 8 63 Phagosome
KEGG KEGG:03060 0.01726 4.710 1.033 4 20 Protein export
KEGG KEGG:03013 0.04024 1.955 6.149 11 119 RNA transport
GO: Biological process GO:0006518 0.00000 20.136 6.672 51 175 peptide metabolic process
GO: Biological process GO:0043604 0.00000 20.381 6.405 50 168 amide biosynthetic process
GO: Biological process GO:0006412 0.00000 21.247 5.361 45 147 translation
GO: Biological process GO:1901566 0.00000 12.811 10.827 56 284 organonitrogen compound biosynthetic process
GO: Biological process GO:0019538 0.00000 11.237 11.290 53 307 protein metabolic process
GO: Biological process GO:0009059 0.00000 4.098 21.426 51 562 macromolecule biosynthetic process
GO: Biological process GO:0044249 0.00000 3.392 29.203 57 766 cellular biosynthetic process
GO: Biological process GO:0034641 0.00000 3.060 33.931 60 890 cellular nitrogen compound metabolic process
GO: Biological process GO:0044260 0.00000 2.998 35.303 61 926 cellular macromolecule metabolic process
GO: Biological process GO:0071704 0.00001 2.652 55.242 76 1449 organic substance metabolic process
GO: Biological process GO:0006414 0.00413 52.000 0.113 2 3 translational elongation
GO: Biological process GO:0071826 0.01358 4.964 0.953 4 25 ribonucleoprotein complex subunit organization
GO: Biological process GO:0016485 0.01953 12.852 0.229 2 6 protein processing
GO: Biological process GO:0006417 0.02478 5.543 0.648 3 17 regulation of translation
GO: Biological process GO:0015991 0.02478 5.543 0.648 3 17 ATP hydrolysis coupled proton transport
GO: Biological process GO:0019805 0.03812 Inf 0.038 1 1 quinolinate biosynthetic process
GO: Biological process GO:1902001 0.03812 Inf 0.038 1 1 fatty acid transmembrane transport
GO: Biological process GO:0006231 0.03812 Inf 0.038 1 1 dTMP biosynthetic process
GO: Biological process GO:0045900 0.03812 Inf 0.038 1 1 negative regulation of translational elongation
GO: Biological process GO:1903825 0.03812 Inf 0.038 1 1 organic acid transmembrane transport
GO: Biological process GO:0009157 0.03812 Inf 0.038 1 1 deoxyribonucleoside monophosphate biosynthetic process
GO: Biological process GO:0009176 0.03812 Inf 0.038 1 1 pyrimidine deoxyribonucleoside monophosphate metabolic process
GO: Biological process GO:0043420 0.03812 Inf 0.038 1 1 anthranilate metabolic process
GO: Biological process GO:0006069 0.03812 Inf 0.038 1 1 ethanol oxidation
GO: Biological process GO:0034354 0.03812 Inf 0.038 1 1 ‘de novo’ NAD biosynthetic process from tryptophan
GO: Biological process GO:0034308 0.03812 Inf 0.038 1 1 primary alcohol metabolic process
GO: Biological process GO:0000028 0.03812 Inf 0.038 1 1 ribosomal small subunit assembly
GO: Biological process GO:0030163 0.04027 2.576 2.554 6 67 protein catabolic process
GO: Molecular function GO:0003735 0.00000 43.470 2.977 47 107 structural constituent of ribosome
GO: Molecular function GO:0004298 0.00001 25.966 0.334 5 12 threonine-type endopeptidase activity
GO: Molecular function GO:0003723 0.00002 3.919 4.841 16 178 RNA binding
GO: Molecular function GO:0005544 0.00226 71.016 0.083 2 3 calcium-dependent phospholipid binding
GO: Molecular function GO:0003743 0.00394 7.188 0.668 4 24 translation initiation factor activity
GO: Molecular function GO:0019843 0.01449 14.307 0.193 2 7 rRNA binding
GO: Molecular function GO:0008097 0.02782 Inf 0.028 1 1 5S rRNA binding
GO: Molecular function GO:0004799 0.02782 Inf 0.028 1 1 thymidylate synthase activity
GO: Molecular function GO:0051903 0.02782 Inf 0.028 1 1 S-(hydroxymethyl)glutathione dehydrogenase activity
GO: Molecular function GO:0004852 0.02782 Inf 0.028 1 1 uroporphyrinogen-III synthase activity
GO: Molecular function GO:0033925 0.02782 Inf 0.028 1 1 mannosyl-glycoprotein endo-beta-N-acetylglucosaminidase activity
GO: Molecular function GO:0003922 0.02782 Inf 0.028 1 1 GMP synthase (glutamine-hydrolyzing) activity
GO: Molecular function GO:0004502 0.02782 Inf 0.028 1 1 kynurenine 3-monooxygenase activity
GO: Molecular function GO:0004427 0.02782 Inf 0.028 1 1 inorganic diphosphatase activity
GO: Molecular function GO:0004639 0.02782 Inf 0.028 1 1 phosphoribosylaminoimidazolesuccinocarboxamide synthase activity
GO: Molecular function GO:0070273 0.02782 Inf 0.028 1 1 phosphatidylinositol-4-phosphate binding
GO: Molecular function GO:0008609 0.02782 Inf 0.028 1 1 alkylglycerone-phosphate synthase activity
GO: Cellular component GO:0005840 0.00000 32.684 3.774 47 111 ribosome
GO: Cellular component GO:0005737 0.00000 6.991 21.385 71 629 cytoplasm
GO: Cellular component GO:0043228 0.00000 8.045 11.220 51 330 non-membrane-bounded organelle
GO: Cellular component GO:0032991 0.00000 5.783 21.147 65 622 macromolecular complex
GO: Cellular component GO:0043229 0.00000 3.425 21.122 47 664 intracellular organelle
GO: Cellular component GO:0005622 0.00000 2.879 56.098 87 1650 intracellular
GO: Cellular component GO:0015934 0.00000 49.270 0.272 5 8 large ribosomal subunit
GO: Cellular component GO:0015935 0.00000 37.563 0.301 5 9 small ribosomal subunit
GO: Cellular component GO:0005623 0.00000 2.355 63.340 88 1863 cell
GO: Cellular component GO:1905369 0.00033 10.525 0.646 5 19 endopeptidase complex
GO: Cellular component GO:0005839 0.00068 29.521 0.201 3 6 proteasome core complex
GO: Cellular component GO:0022627 0.00115 Inf 0.068 2 2 cytosolic small ribosomal subunit
GO: Cellular component GO:0030529 0.00832 4.415 1.275 5 58 intracellular ribonucleoprotein complex
GO: Cellular component GO:0019773 0.02153 11.532 0.238 2 7 proteasome core complex, alpha-subunit complex
GO: Cellular component GO:0033179 0.02153 11.532 0.238 2 7 proton-transporting V-type ATPase, V0 domain
GO: Cellular component GO:0016607 0.03400 Inf 0.034 1 1 nuclear speck
GO: Cellular component GO:0030014 0.03400 Inf 0.034 1 1 CCR4-NOT complex
GO: Cellular component GO:0044446 0.04093 1.573 15.911 23 468 intracellular organelle part
GO: Cellular component GO:0016469 0.04614 4.134 0.816 3 24 proton-transporting two-sector ATPase complex



Table S16: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the queen pheromone treatment in A. mellifera. The gene universe was defined as all A. mellifera genes measured in this study.

up.in.QP.apis <- (apis.de %>% filter(`Log2 FC` < 0) %>% as.data.frame())$Gene
GO.and.KEGG.enrichment(up.in.QP.apis, gene.universe.apis) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:00250 0.01180 14.422 0.169 2 25 Alanine, aspartate and glutamate metabolism
KEGG KEGG:00630 0.01273 13.815 0.176 2 26 Glyoxylate and dicarboxylate metabolism
KEGG KEGG:01200 0.02283 5.782 0.630 3 93 Carbon metabolism
GO: Biological process GO:0032273 0.01173 14.344 0.169 2 17 positive regulation of protein polymerization
GO: Biological process GO:0051495 0.01312 13.443 0.178 2 18 positive regulation of cytoskeleton organization
GO: Biological process GO:0044089 0.01457 12.647 0.188 2 19 positive regulation of cellular component biogenesis
GO: Biological process GO:0051130 0.01768 11.307 0.208 2 21 positive regulation of cellular component organization
GO: Biological process GO:0043254 0.01768 11.307 0.208 2 21 regulation of protein complex assembly
GO: Biological process GO:0001678 0.01973 103.840 0.020 1 2 cellular glucose homeostasis
GO: Biological process GO:0006537 0.01973 103.840 0.020 1 2 glutamate biosynthetic process
GO: Biological process GO:0033500 0.01973 103.840 0.020 1 2 carbohydrate homeostasis
GO: Biological process GO:0043044 0.02945 51.900 0.030 1 3 ATP-dependent chromatin remodeling
GO: Biological process GO:0043623 0.03256 7.932 0.287 2 29 cellular protein complex assembly
GO: Biological process GO:0015980 0.03467 7.646 0.297 2 30 energy derivation by oxidation of organic compounds
GO: Biological process GO:0007050 0.03909 34.587 0.040 1 4 cell cycle arrest
GO: Biological process GO:0006388 0.03909 34.587 0.040 1 4 tRNA splicing, via endonucleolytic cleavage and ligation
GO: Biological process GO:0090063 0.04863 25.930 0.050 1 5 positive regulation of microtubule nucleation
GO: Biological process GO:0031113 0.04863 25.930 0.050 1 5 regulation of microtubule polymerization
GO: Molecular function GO:0005242 0.00011 Inf 0.021 2 2 inward rectifier potassium channel activity
GO: Molecular function GO:0004114 0.00293 32.622 0.084 2 8 3’,5’-cyclic-nucleotide phosphodiesterase activity
GO: Molecular function GO:0030246 0.00366 11.068 0.316 3 30 carbohydrate binding
GO: Molecular function GO:0015930 0.01055 Inf 0.011 1 1 glutamate synthase activity
GO: Molecular function GO:0016639 0.01055 Inf 0.011 1 1 oxidoreductase activity, acting on the CH-NH2 group of donors, NAD or NADP as acceptor
GO: Molecular function GO:0004108 0.01055 Inf 0.011 1 1 citrate (Si)-synthase activity
GO: Molecular function GO:0022843 0.01338 13.022 0.179 2 17 voltage-gated cation channel activity
GO: Molecular function GO:0008081 0.02012 10.271 0.221 2 21 phosphoric diester hydrolase activity
GO: Molecular function GO:0004396 0.02098 95.848 0.021 1 2 hexokinase activity
GO: Molecular function GO:0005536 0.02098 95.848 0.021 1 2 glucose binding
GO: Molecular function GO:0022832 0.02592 8.865 0.253 2 24 voltage-gated channel activity
GO: Molecular function GO:0005267 0.02799 8.477 0.264 2 25 potassium channel activity
GO: Molecular function GO:0016788 0.02882 2.814 2.362 6 224 hydrolase activity, acting on ester bonds
GO: Molecular function GO:0034979 0.03131 47.913 0.032 1 3 NAD-dependent protein deacetylase activity
GO: Molecular function GO:0032041 0.03131 47.913 0.032 1 3 NAD-dependent histone deacetylase activity (H3-K14 specific)
GO: Molecular function GO:0004407 0.03131 47.913 0.032 1 3 histone deacetylase activity
GO: Molecular function GO:0000213 0.03131 47.913 0.032 1 3 tRNA-intron endonuclease activity
GO: Molecular function GO:0019213 0.04153 31.935 0.042 1 4 deacetylase activity
GO: Molecular function GO:0046912 0.04153 31.935 0.042 1 4 transferase activity, transferring acyl groups, acyl groups converted into alkyl on transfer
GO: Molecular function GO:0017150 0.04153 31.935 0.042 1 4 tRNA dihydrouridine synthase activity
GO: Cellular component GO:0005815 0.00842 17.054 0.142 2 15 microtubule organizing center
GO: Cellular component GO:0016514 0.00944 Inf 0.009 1 1 SWI/SNF complex
GO: Cellular component GO:0000118 0.00944 Inf 0.009 1 1 histone deacetylase complex
GO: Cellular component GO:0016012 0.02807 53.956 0.028 1 3 sarcoglycan complex
GO: Cellular component GO:0005761 0.04636 26.963 0.047 1 5 mitochondrial ribosome

KEGG and GO enrichment for differentially expressed genes in L. flavus

Table S17: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the control group in L. flavus. The gene universe was defined as all L. flavus genes for which we detected an A. mellifera ortholog.

# The gene universe is all L. flavus genes for which we found a BLAST hit in Apis mellifera
gene.universe.flavus <- (left_join(tbl(my_db, "rsem_lf") %>% 
                                     dplyr::select(gene),  
                                   tbl(my_db, "lf2am") %>% 
                                     dplyr::rename(gene = lf), by = "gene") %>% 
                           dplyr::select(am) %>% 
                           filter(!is.na(am)) %>% 
                           as.data.frame())[,1] %>% unique
# The test set is all differentially expressed genes in L. flavus for which we found a BLAST hit in Apis
up.in.control.flavus <- (flavus.de %>% filter(`Log2 FC` > 0 & `Apis BLAST` != " ") %>% as.data.frame())$`Apis BLAST` %>% unique

GO.and.KEGG.enrichment(up.in.control.flavus, gene.universe.flavus)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04142 0.01744 6.386 0.568 3 41 Lysosome
GO: Biological process GO:0042278 0.00412 11.415 0.340 3 30 purine nucleoside metabolic process
GO: Biological process GO:0015991 0.00519 24.375 0.113 2 10 ATP hydrolysis coupled proton transport
GO: Biological process GO:0009119 0.00750 9.024 0.420 3 37 ribonucleoside metabolic process
GO: Biological process GO:1901657 0.01000 8.053 0.465 3 41 glycosyl compound metabolic process
GO: Biological process GO:0006422 0.01135 Inf 0.011 1 1 aspartyl-tRNA aminoacylation
GO: Biological process GO:0006285 0.01135 Inf 0.011 1 1 base-excision repair, AP site formation
GO: Biological process GO:0003012 0.01135 Inf 0.011 1 1 muscle system process
GO: Biological process GO:0031032 0.01135 Inf 0.011 1 1 actomyosin structure organization
GO: Biological process GO:0006937 0.01135 Inf 0.011 1 1 regulation of muscle contraction
GO: Biological process GO:1902600 0.01171 14.952 0.170 2 15 hydrogen ion transmembrane transport
GO: Biological process GO:0098660 0.01171 14.952 0.170 2 15 inorganic ion transmembrane transport
GO: Biological process GO:0098655 0.01171 14.952 0.170 2 15 cation transmembrane transport
GO: Biological process GO:0006818 0.01329 13.875 0.182 2 16 hydrogen transport
GO: Biological process GO:0046034 0.01672 12.125 0.204 2 18 ATP metabolic process
GO: Biological process GO:0015672 0.01856 11.404 0.216 2 19 monovalent inorganic cation transport
GO: Biological process GO:0009144 0.02249 10.191 0.238 2 21 purine nucleoside triphosphate metabolic process
GO: Biological process GO:0044057 0.02258 92.176 0.023 1 2 regulation of system process
GO: Biological process GO:0000096 0.02258 92.176 0.023 1 2 sulfur amino acid metabolic process
GO: Biological process GO:0019284 0.02258 92.176 0.023 1 2 L-methionine biosynthetic process from S-adenosylmethionine
GO: Biological process GO:0046498 0.02258 92.176 0.023 1 2 S-adenosylhomocysteine metabolic process
GO: Biological process GO:0009199 0.02674 9.208 0.261 2 23 ribonucleoside triphosphate metabolic process
GO: Biological process GO:0009126 0.03366 8.042 0.295 2 26 purine nucleoside monophosphate metabolic process
GO: Biological process GO:0019509 0.03368 46.059 0.034 1 3 L-methionine biosynthetic process from methylthioadenosine
GO: Biological process GO:0071265 0.03368 46.059 0.034 1 3 L-methionine biosynthetic process
GO: Biological process GO:0043102 0.03368 46.059 0.034 1 3 amino acid salvage
GO: Biological process GO:0007205 0.03368 46.059 0.034 1 3 protein kinase C-activating G-protein coupled receptor signaling pathway
GO: Biological process GO:0055085 0.03452 4.858 0.738 3 65 transmembrane transport
GO: Biological process GO:0009161 0.04387 6.875 0.340 2 30 ribonucleoside monophosphate metabolic process
GO: Biological process GO:0009067 0.04467 30.686 0.045 1 4 aspartate family amino acid biosynthetic process
GO: Biological process GO:0042181 0.04467 30.686 0.045 1 4 ketone biosynthetic process
GO: Biological process GO:0006108 0.04467 30.686 0.045 1 4 malate metabolic process
GO: Biological process GO:0006744 0.04467 30.686 0.045 1 4 ubiquinone biosynthetic process
GO: Biological process GO:0006555 0.04467 30.686 0.045 1 4 methionine metabolic process
GO: Biological process GO:1901661 0.04467 30.686 0.045 1 4 quinone metabolic process
GO: Biological process GO:0055086 0.04484 4.345 0.817 3 72 nucleobase-containing small molecule metabolic process
GO: Biological process GO:0006163 0.04658 6.634 0.352 2 31 purine nucleotide metabolic process
GO: Molecular function GO:0044769 0.00552 23.648 0.117 2 8 ATPase activity, coupled to transmembrane movement of ions, rotational mechanism
GO: Molecular function GO:0008169 0.01463 Inf 0.015 1 1 C-methyltransferase activity
GO: Molecular function GO:0004054 0.01463 Inf 0.015 1 1 arginine kinase activity
GO: Molecular function GO:0019104 0.01463 Inf 0.015 1 1 DNA N-glycosylase activity
GO: Molecular function GO:0000703 0.01463 Inf 0.015 1 1 oxidized pyrimidine nucleobase lesion DNA N-glycosylase activity
GO: Molecular function GO:0004815 0.01463 Inf 0.015 1 1 aspartate-tRNA ligase activity
GO: Molecular function GO:0046570 0.01463 Inf 0.015 1 1 methylthioribulose 1-phosphate dehydratase activity
GO: Molecular function GO:0008425 0.01463 Inf 0.015 1 1 2-polyprenyl-6-methoxy-1,4-benzoquinone methyltransferase activity
GO: Molecular function GO:0019829 0.01468 12.874 0.190 2 13 cation-transporting ATPase activity
GO: Molecular function GO:0016835 0.02197 10.103 0.234 2 16 carbon-oxygen lyase activity
GO: Molecular function GO:0022853 0.02468 9.426 0.249 2 17 active ion transmembrane transporter activity
GO: Molecular function GO:0046872 0.02757 2.074 8.425 14 576 metal ion binding
GO: Molecular function GO:0030151 0.02904 69.162 0.029 1 2 molybdenum ion binding
GO: Molecular function GO:0004471 0.02904 69.162 0.029 1 2 malate dehydrogenase (decarboxylating) (NAD+) activity
GO: Molecular function GO:0016972 0.02904 69.162 0.029 1 2 thiol oxidase activity
GO: Molecular function GO:0015078 0.03673 7.430 0.307 2 21 hydrogen ion transmembrane transporter activity
GO: Molecular function GO:0043167 0.03923 1.956 8.805 14 602 ion binding
GO: Molecular function GO:0004181 0.04326 34.568 0.044 1 3 metallocarboxypeptidase activity
GO: Molecular function GO:0004143 0.04326 34.568 0.044 1 3 diacylglycerol kinase activity
GO: Molecular function GO:0015399 0.04346 6.717 0.336 2 23 primary active transmembrane transporter activity
GO: Molecular function GO:0042626 0.04346 6.717 0.336 2 23 ATPase activity, coupled to transmembrane movement of substances
GO: Molecular function GO:0003824 0.04989 1.861 20.521 26 1403 catalytic activity
GO: Cellular component GO:0043292 0.00009 Inf 0.020 2 2 contractile fiber
GO: Cellular component GO:0005861 0.00009 Inf 0.020 2 2 troponin complex
GO: Cellular component GO:0036379 0.00009 Inf 0.020 2 2 myofilament
GO: Cellular component GO:0030017 0.00009 Inf 0.020 2 2 sarcomere
GO: Cellular component GO:0016469 0.00902 16.947 0.148 2 15 proton-transporting two-sector ATPase complex
GO: Cellular component GO:0042600 0.00987 Inf 0.010 1 1 chorion
GO: Cellular component GO:0005623 0.02283 2.921 11.028 16 1117 cell
GO: Cellular component GO:0015629 0.02430 9.533 0.247 2 25 actin cytoskeleton
GO: Cellular component GO:0033180 0.02934 52.600 0.030 1 3 proton-transporting V-type ATPase, V1 domain
GO: Cellular component GO:0045261 0.03894 35.050 0.039 1 4 proton-transporting ATP synthase complex, catalytic core F(1)



Table S18: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the queen pheromone treatment in L. flavus. The gene universe was defined as all L. flavus genes for which we detected an A. mellifera ortholog.

up.in.QP.flavus <- (flavus.de %>% filter(`Log2 FC` < 0 & `Apis BLAST` != " ") %>% as.data.frame())$`Apis BLAST` %>% unique
GO.and.KEGG.enrichment(up.in.QP.flavus, gene.universe.flavus) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04146 0.00009 10.553 0.798 6 39 Peroxisome
KEGG KEGG:04141 0.00089 5.557 1.657 7 81 Protein processing in endoplasmic reticulum
KEGG KEGG:01212 0.00157 9.845 0.532 4 26 Fatty acid metabolism
KEGG KEGG:00030 0.00243 14.347 0.286 3 14 Pentose phosphate pathway
KEGG KEGG:01200 0.00507 5.296 1.166 5 57 Carbon metabolism
KEGG KEGG:00071 0.00699 9.246 0.409 3 20 Fatty acid degradation
KEGG KEGG:01040 0.00799 20.400 0.143 2 7 Biosynthesis of unsaturated fatty acids
KEGG KEGG:00981 0.00799 20.400 0.143 2 7 Insect hormone biosynthesis
KEGG KEGG:00061 0.01051 16.989 0.164 2 8 Fatty acid biosynthesis
KEGG KEGG:00062 0.01987 11.303 0.225 2 11 Fatty acid elongation
KEGG KEGG:03050 0.02168 5.782 0.614 3 30 Proteasome
KEGG KEGG:00052 0.02355 10.166 0.246 2 12 Galactose metabolism
KEGG KEGG:01230 0.03262 4.862 0.716 3 35 Biosynthesis of amino acids
KEGG KEGG:00410 0.03606 7.804 0.307 2 15 beta-Alanine metabolism
KEGG KEGG:00380 0.03606 7.804 0.307 2 15 Tryptophan metabolism
GO: Biological process GO:0006098 0.00119 65.208 0.057 2 5 pentose-phosphate shunt
GO: Biological process GO:0006081 0.00119 65.208 0.057 2 5 cellular aldehyde metabolic process
GO: Biological process GO:0006629 0.00633 6.607 0.783 4 69 lipid metabolic process
GO: Biological process GO:0046496 0.01022 16.208 0.159 2 14 nicotinamide nucleotide metabolic process
GO: Biological process GO:0006102 0.01135 Inf 0.011 1 1 isocitrate metabolic process
GO: Biological process GO:0044242 0.01135 Inf 0.011 1 1 cellular lipid catabolic process
GO: Biological process GO:0015910 0.01135 Inf 0.011 1 1 peroxisomal long-chain fatty acid import
GO: Biological process GO:0015908 0.01135 Inf 0.011 1 1 fatty acid transport
GO: Biological process GO:0006635 0.01135 Inf 0.011 1 1 fatty acid beta-oxidation
GO: Biological process GO:0034440 0.01135 Inf 0.011 1 1 lipid oxidation
GO: Biological process GO:0072329 0.01135 Inf 0.011 1 1 monocarboxylic acid catabolic process
GO: Biological process GO:0072524 0.01171 14.952 0.170 2 15 pyridine-containing compound metabolic process
GO: Biological process GO:0006631 0.01329 13.875 0.182 2 16 fatty acid metabolic process
GO: Biological process GO:0006733 0.01672 12.125 0.204 2 18 oxidoreduction coenzyme metabolic process
GO: Biological process GO:0044281 0.01784 3.583 2.247 6 198 small molecule metabolic process
GO: Biological process GO:0005991 0.02258 92.176 0.023 1 2 trehalose metabolic process
GO: Biological process GO:0006012 0.03368 46.059 0.034 1 3 galactose metabolic process
GO: Biological process GO:0046942 0.03368 46.059 0.034 1 3 carboxylic acid transport
GO: Biological process GO:0009311 0.04467 30.686 0.045 1 4 oligosaccharide metabolic process
GO: Biological process GO:0006820 0.04467 30.686 0.045 1 4 anion transport
GO: Biological process GO:0005975 0.04484 4.345 0.817 3 72 carbohydrate metabolic process
GO: Molecular function GO:0016491 0.00459 3.556 2.730 8 184 oxidoreductase activity
GO: Molecular function GO:0033961 0.01578 Inf 0.016 1 1 cis-stilbene-oxide hydrolase activity
GO: Molecular function GO:0004801 0.01578 Inf 0.016 1 1 sedoheptulose-7-phosphate:D-glyceraldehyde-3-phosphate glyceronetransferase activity
GO: Molecular function GO:0004335 0.01578 Inf 0.016 1 1 galactokinase activity
GO: Molecular function GO:0004300 0.01578 Inf 0.016 1 1 enoyl-CoA hydratase activity
GO: Molecular function GO:0004450 0.01578 Inf 0.016 1 1 isocitrate dehydrogenase (NADP+) activity
GO: Molecular function GO:0016620 0.01698 11.869 0.205 2 13 oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor
GO: Molecular function GO:0016614 0.01955 5.858 0.584 3 37 oxidoreductase activity, acting on CH-OH group of donors
GO: Molecular function GO:0004784 0.03132 63.900 0.032 1 2 superoxide dismutase activity
GO: Molecular function GO:0003756 0.03132 63.900 0.032 1 2 protein disulfide isomerase activity
GO: Molecular function GO:0004555 0.03132 63.900 0.032 1 2 alpha,alpha-trehalase activity
GO: Molecular function GO:0031177 0.03132 63.900 0.032 1 2 phosphopantetheine binding
GO: Molecular function GO:0003857 0.03132 63.900 0.032 1 2 3-hydroxyacyl-CoA dehydrogenase activity
GO: Molecular function GO:0004185 0.03132 63.900 0.032 1 2 serine-type carboxypeptidase activity
GO: Molecular function GO:0016787 0.03223 2.005 8.555 14 555 hydrolase activity
GO: Molecular function GO:0016801 0.04662 31.938 0.047 1 3 hydrolase activity, acting on ether bonds
GO: Molecular function GO:0004616 0.04662 31.938 0.047 1 3 phosphogluconate dehydrogenase (decarboxylating) activity
GO: Cellular component GO:0005737 0.00040 4.662 4.444 12 411 cytoplasm
GO: Cellular component GO:0016507 0.01081 Inf 0.011 1 1 mitochondrial fatty acid beta-oxidation multienzyme complex
GO: Cellular component GO:0017119 0.03211 47.773 0.032 1 3 Golgi transport complex
GO: Cellular component GO:0005783 0.04558 6.584 0.346 2 32 endoplasmic reticulum

KEGG and GO enrichment for differentially expressed genes in L. niger

Table S19: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the control group in L. niger The gene universe was defined as all L. niger genes for which we detected an A. mellifera ortholog.

# The gene universe is all L. flavus genes for which we found a BLAST hit in Apis mellifera
gene.universe.niger <- (left_join(tbl(my_db, "rsem_ln") %>% 
                                    dplyr::select(gene), 
                                  tbl(my_db, "ln2am") %>%  
                                    dplyr::rename(gene = ln), by = "gene") %>% 
                          dplyr::select(am) %>% 
                          filter(!is.na(am)) %>% 
                          as.data.frame())[,1] %>% unique
# The test set is all differentially expressed genes in L. flavus for which we found a BLAST hit in Apis
up.in.control.niger <- (niger.de %>% filter(`Log2 FC` > 0 & `Apis BLAST` != " ") %>% as.data.frame())$`Apis BLAST` %>% unique

GO.and.KEGG.enrichment(up.in.control.niger, gene.universe.niger) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04145 0.00336 12.834 0.322 3 35 Phagosome
KEGG KEGG:01230 0.00426 11.709 0.349 3 38 Biosynthesis of amino acids
KEGG KEGG:04745 0.00489 25.291 0.110 2 12 Phototransduction - fly
KEGG KEGG:01100 0.00511 5.064 4.045 9 440 Metabolic pathways
KEGG KEGG:00030 0.00575 22.975 0.120 2 13 Pentose phosphate pathway
KEGG KEGG:00330 0.00575 22.975 0.120 2 13 Arginine and proline metabolism
KEGG KEGG:04391 0.02240 10.432 0.239 2 26 Hippo signaling pathway - fly
KEGG KEGG:00920 0.02735 58.292 0.028 1 3 Sulfur metabolism
KEGG KEGG:00603 0.04519 29.104 0.046 1 5 Glycosphingolipid biosynthesis - globo series
KEGG KEGG:00130 0.04519 29.104 0.046 1 5 Ubiquinone and other terpenoid-quinone biosynthesis
GO: Biological process GO:0006753 0.00096 12.285 0.484 4 57 nucleoside phosphate metabolic process
GO: Biological process GO:0009126 0.00099 20.400 0.212 3 25 purine nucleoside monophosphate metabolic process
GO: Biological process GO:0006163 0.00154 17.215 0.246 3 29 purine nucleotide metabolic process
GO: Biological process GO:0042278 0.00154 17.215 0.246 3 29 purine nucleoside metabolic process
GO: Biological process GO:0009161 0.00154 17.215 0.246 3 29 ribonucleoside monophosphate metabolic process
GO: Biological process GO:0044281 0.00158 7.319 1.478 6 188 small molecule metabolic process
GO: Biological process GO:0009259 0.00225 14.880 0.280 3 33 ribonucleotide metabolic process
GO: Biological process GO:0009119 0.00268 13.931 0.297 3 35 ribonucleoside metabolic process
GO: Biological process GO:1901657 0.00340 12.711 0.323 3 38 glycosyl compound metabolic process
GO: Biological process GO:0019362 0.00493 24.909 0.110 2 13 pyridine nucleotide metabolic process
GO: Biological process GO:0009168 0.00747 19.532 0.136 2 16 purine ribonucleoside monophosphate biosynthetic process
GO: Biological process GO:0006793 0.00803 6.511 0.858 4 101 phosphorus metabolic process
GO: Biological process GO:0046034 0.00843 18.218 0.144 2 17 ATP metabolic process
GO: Biological process GO:0031032 0.00849 Inf 0.008 1 1 actomyosin structure organization
GO: Biological process GO:0046129 0.00944 17.068 0.153 2 18 purine ribonucleoside biosynthetic process
GO: Biological process GO:0009152 0.01050 16.053 0.161 2 19 purine ribonucleotide biosynthetic process
GO: Biological process GO:0009144 0.01161 15.152 0.170 2 20 purine nucleoside triphosphate metabolic process
GO: Biological process GO:0009124 0.01277 14.344 0.178 2 21 nucleoside monophosphate biosynthetic process
GO: Biological process GO:0009199 0.01398 13.618 0.187 2 22 ribonucleoside triphosphate metabolic process
GO: Biological process GO:0072522 0.01523 12.961 0.195 2 23 purine-containing compound biosynthetic process
GO: Biological process GO:0044699 0.01590 4.333 5.689 10 670 single-organism process
GO: Biological process GO:0009163 0.01654 12.364 0.204 2 24 nucleoside biosynthetic process
GO: Biological process GO:0046390 0.01654 12.364 0.204 2 24 ribose phosphate biosynthetic process
GO: Biological process GO:0044208 0.01692 126.417 0.017 1 2 ‘de novo’ AMP biosynthetic process
GO: Biological process GO:0055129 0.01692 126.417 0.017 1 2 L-proline biosynthetic process
GO: Biological process GO:0006165 0.02527 63.167 0.025 1 3 nucleoside diphosphate phosphorylation
GO: Biological process GO:0006560 0.02527 63.167 0.025 1 3 proline metabolic process
GO: Biological process GO:0006096 0.02527 63.167 0.025 1 3 glycolytic process
GO: Biological process GO:0006189 0.03357 42.083 0.034 1 4 ‘de novo’ IMP biosynthetic process
GO: Biological process GO:0046040 0.03357 42.083 0.034 1 4 IMP metabolic process
GO: Biological process GO:0046033 0.03357 42.083 0.034 1 4 AMP metabolic process
GO: Biological process GO:0006732 0.03382 8.182 0.297 2 35 coenzyme metabolic process
GO: Biological process GO:1901564 0.03621 3.609 2.007 5 255 organonitrogen compound metabolic process
GO: Biological process GO:0009165 0.03750 7.704 0.314 2 37 nucleotide biosynthetic process
GO: Biological process GO:0009084 0.04179 31.542 0.042 1 5 glutamine family amino acid biosynthetic process
GO: Biological process GO:0006730 0.04179 31.542 0.042 1 5 one-carbon metabolic process
GO: Biological process GO:0009185 0.04179 31.542 0.042 1 5 ribonucleoside diphosphate metabolic process
GO: Biological process GO:0009135 0.04179 31.542 0.042 1 5 purine nucleoside diphosphate metabolic process
GO: Biological process GO:0006098 0.04179 31.542 0.042 1 5 pentose-phosphate shunt
GO: Biological process GO:0046031 0.04179 31.542 0.042 1 5 ADP metabolic process
GO: Biological process GO:0006081 0.04179 31.542 0.042 1 5 cellular aldehyde metabolic process
GO: Biological process GO:0016052 0.04179 31.542 0.042 1 5 carbohydrate catabolic process
GO: Biological process GO:0009072 0.04996 25.217 0.051 1 6 aromatic amino acid family metabolic process
GO: Biological process GO:0006979 0.04996 25.217 0.051 1 6 response to oxidative stress
GO: Molecular function GO:0020037 0.00007 24.157 0.234 4 28 heme binding
GO: Molecular function GO:0004054 0.00837 Inf 0.008 1 1 arginine kinase activity
GO: Molecular function GO:0004018 0.00837 Inf 0.008 1 1 N6-(1,2-dicarboxyethyl)AMP AMP-lyase (fumarate-forming) activity
GO: Molecular function GO:0016840 0.00837 Inf 0.008 1 1 carbon-nitrogen lyase activity
GO: Molecular function GO:0004801 0.00837 Inf 0.008 1 1 sedoheptulose-7-phosphate:D-glyceraldehyde-3-phosphate glyceronetransferase activity
GO: Molecular function GO:0004332 0.00837 Inf 0.008 1 1 fructose-bisphosphate aldolase activity
GO: Molecular function GO:0070626 0.00837 Inf 0.008 1 1 (S)-2-(5-amino-1-(5-phospho-D-ribosyl)imidazole-4-carboxamido)succinate AMP-lyase (fumarate-forming) activity
GO: Molecular function GO:0003868 0.00837 Inf 0.008 1 1 4-hydroxyphenylpyruvate dioxygenase activity
GO: Molecular function GO:0004013 0.01667 124.350 0.017 1 2 adenosylhomocysteinase activity
GO: Molecular function GO:0004735 0.01667 124.350 0.017 1 2 pyrroline-5-carboxylate reductase activity
GO: Molecular function GO:0004497 0.01922 10.807 0.218 2 26 monooxygenase activity
GO: Molecular function GO:0016701 0.02491 62.150 0.025 1 3 oxidoreductase activity, acting on single donors with incorporation of molecular oxygen
GO: Molecular function GO:0016801 0.02491 62.150 0.025 1 3 hydrolase activity, acting on ether bonds
GO: Molecular function GO:0005506 0.02521 9.248 0.251 2 30 iron ion binding
GO: Molecular function GO:0016705 0.03015 8.343 0.276 2 33 oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen
GO: Molecular function GO:0051213 0.03308 41.417 0.033 1 4 dioxygenase activity
GO: Molecular function GO:0004601 0.03308 41.417 0.033 1 4 peroxidase activity
GO: Molecular function GO:0046933 0.04923 24.830 0.050 1 6 proton-transporting ATP synthase activity, rotational mechanism
GO: Molecular function GO:0016645 0.04923 24.830 0.050 1 6 oxidoreductase activity, acting on the CH-NH group of donors
GO: Cellular component GO:0005856 0.00494 11.488 0.373 3 75 cytoskeleton
GO: Cellular component GO:0042600 0.00497 Inf 0.005 1 1 chorion
GO: Cellular component GO:0043292 0.00497 Inf 0.005 1 1 contractile fiber
GO: Cellular component GO:0005861 0.00497 Inf 0.005 1 1 troponin complex
GO: Cellular component GO:0036379 0.00497 Inf 0.005 1 1 myofilament
GO: Cellular component GO:0030017 0.00497 Inf 0.005 1 1 sarcomere
GO: Cellular component GO:0044422 0.00666 6.360 1.377 5 277 organelle part
GO: Cellular component GO:0005758 0.01484 111.111 0.015 1 3 mitochondrial intermembrane space
GO: Cellular component GO:0031967 0.01568 12.921 0.199 2 40 organelle envelope
GO: Cellular component GO:0045261 0.01975 74.037 0.020 1 4 proton-transporting ATP synthase complex, catalytic core F(1)
GO: Cellular component GO:0005737 0.02916 4.173 1.948 5 392 cytoplasm
GO: Cellular component GO:0070469 0.03433 36.963 0.035 1 7 respiratory chain
GO: Cellular component GO:0005739 0.03479 8.233 0.303 2 61 mitochondrion
GO: Cellular component GO:0016459 0.04871 24.605 0.050 1 10 myosin complex



Table S20: Results of KEGG and GO enrichment analysis on the list of genes that were significantly upregulated in the queen pheromone treatment in L. niger The gene universe was defined as all L. niger genes for which we detected an A. mellifera ortholog.

up.in.QP.niger <- (niger.de %>% filter(`Log2 FC` < 0 & `Apis BLAST` != " ") %>% as.data.frame())$`Apis BLAST` %>% unique
GO.and.KEGG.enrichment(up.in.QP.niger, gene.universe.niger)  
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:01200 0.00004 13.186 0.726 6 57 Carbon metabolism
KEGG KEGG:01212 0.00230 14.495 0.280 3 22 Fatty acid metabolism
KEGG KEGG:00061 0.00410 28.958 0.102 2 8 Fatty acid biosynthesis
KEGG KEGG:04146 0.00682 9.428 0.407 3 32 Peroxisome
KEGG KEGG:01100 0.00788 3.542 5.601 11 440 Metabolic pathways
KEGG KEGG:00030 0.01099 15.739 0.165 2 13 Pentose phosphate pathway
KEGG KEGG:00640 0.01860 11.508 0.216 2 17 Propanoate metabolism
KEGG KEGG:00620 0.02540 9.569 0.255 2 20 Pyruvate metabolism
GO: Biological process GO:0006733 0.00496 25.100 0.111 2 17 oxidoreduction coenzyme metabolic process
GO: Biological process GO:0042744 0.00653 Inf 0.007 1 1 hydrogen peroxide catabolic process
GO: Biological process GO:0072593 0.00653 Inf 0.007 1 1 reactive oxygen species metabolic process
GO: Biological process GO:0042181 0.02590 56.222 0.026 1 4 ketone biosynthetic process
GO: Biological process GO:0006108 0.02590 56.222 0.026 1 4 malate metabolic process
GO: Biological process GO:0042773 0.02590 56.222 0.026 1 4 ATP synthesis coupled electron transport
GO: Biological process GO:0006744 0.02590 56.222 0.026 1 4 ubiquinone biosynthetic process
GO: Biological process GO:1901661 0.02590 56.222 0.026 1 4 quinone metabolic process
GO: Biological process GO:0044281 0.02780 4.698 1.261 4 193 small molecule metabolic process
GO: Biological process GO:0006098 0.03228 42.139 0.033 1 5 pentose-phosphate shunt
GO: Biological process GO:0006081 0.03228 42.139 0.033 1 5 cellular aldehyde metabolic process
GO: Biological process GO:0006979 0.03862 33.689 0.039 1 6 response to oxidative stress
GO: Biological process GO:0008152 0.04294 6.176 5.950 9 911 metabolic process
GO: Biological process GO:0009117 0.04899 6.792 0.366 2 56 nucleotide metabolic process
GO: Molecular function GO:0031177 0.00007 Inf 0.018 2 2 phosphopantetheine binding
GO: Molecular function GO:0016491 0.00013 10.633 0.889 6 135 oxidoreductase activity
GO: Molecular function GO:0020037 0.00166 15.549 0.246 3 28 heme binding
GO: Molecular function GO:0016627 0.00459 24.770 0.105 2 12 oxidoreductase activity, acting on the CH-CH group of donors
GO: Molecular function GO:0004096 0.00877 Inf 0.009 1 1 catalase activity
GO: Molecular function GO:0008169 0.00877 Inf 0.009 1 1 C-methyltransferase activity
GO: Molecular function GO:0016420 0.00877 Inf 0.009 1 1 malonyltransferase activity
GO: Molecular function GO:0004320 0.00877 Inf 0.009 1 1 oleoyl-[acyl-carrier-protein] hydrolase activity
GO: Molecular function GO:0004313 0.00877 Inf 0.009 1 1 [acyl-carrier-protein] S-acetyltransferase activity
GO: Molecular function GO:0004314 0.00877 Inf 0.009 1 1 [acyl-carrier-protein] S-malonyltransferase activity
GO: Molecular function GO:0004315 0.00877 Inf 0.009 1 1 3-oxoacyl-[acyl-carrier-protein] synthase activity
GO: Molecular function GO:0004316 0.00877 Inf 0.009 1 1 3-oxoacyl-[acyl-carrier-protein] reductase (NADPH) activity
GO: Molecular function GO:0004317 0.00877 Inf 0.009 1 1 3-hydroxypalmitoyl-[acyl-carrier-protein] dehydratase activity
GO: Molecular function GO:0004319 0.00877 Inf 0.009 1 1 enoyl-[acyl-carrier-protein] reductase (NADPH, B-specific) activity
GO: Molecular function GO:0016295 0.00877 Inf 0.009 1 1 myristoyl-[acyl-carrier-protein] hydrolase activity
GO: Molecular function GO:0016296 0.00877 Inf 0.009 1 1 palmitoyl-[acyl-carrier-protein] hydrolase activity
GO: Molecular function GO:0016790 0.00877 Inf 0.009 1 1 thiolester hydrolase activity
GO: Molecular function GO:0008425 0.00877 Inf 0.009 1 1 2-polyprenyl-6-methoxy-1,4-benzoquinone methyltransferase activity
GO: Molecular function GO:0004784 0.01746 118.381 0.018 1 2 superoxide dismutase activity
GO: Molecular function GO:0004471 0.01746 118.381 0.018 1 2 malate dehydrogenase (decarboxylating) (NAD+) activity
GO: Molecular function GO:0004616 0.01746 118.381 0.018 1 2 phosphogluconate dehydrogenase (decarboxylating) activity
GO: Molecular function GO:0004497 0.02101 10.262 0.228 2 26 monooxygenase activity
GO: Molecular function GO:0016614 0.02529 9.233 0.251 2 30 oxidoreductase activity, acting on CH-OH group of donors
GO: Molecular function GO:0005506 0.02753 8.782 0.263 2 30 iron ion binding
GO: Molecular function GO:0016705 0.03289 7.923 0.289 2 33 oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen
GO: Molecular function GO:0016615 0.03464 39.429 0.035 1 4 malate dehydrogenase activity
GO: Molecular function GO:0080019 0.04311 29.560 0.044 1 5 fatty-acyl-CoA reductase (alcohol-forming) activity
GO: Cellular component GO:0016021 0.03529 4.574 4.682 8 942 integral component of membrane
GO: Cellular component GO:0044425 0.04732 4.197 4.896 8 985 membrane part

KEGG and GO enrichment for differentially expressed genes observed in multiple species

Table S21: Results of KEGG and GO enrichment analysis on the list of genes showing significant differential expression in response to queen pheromone in two or more species. The gene universe was defined as all genes for which we found an ortholog in all four species.

overlap.gene.universe <- make.OGGs(c("am", "lf", "ln"))[[2]]$am      # The gene universe is all genes that have orthologs in the 3 species that we tested for overlap
suppressWarnings(GO.and.KEGG.enrichment(all.overlaps, overlap.gene.universe)) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:01200 0.00006 18.047 0.484 5 45 Carbon metabolism
KEGG KEGG:00030 0.00020 39.533 0.129 3 12 Pentose phosphate pathway
KEGG KEGG:01212 0.02001 11.254 0.226 2 21 Fatty acid metabolism
KEGG KEGG:01100 0.02015 3.682 3.982 8 370 Metabolic pathways
KEGG KEGG:01230 0.04170 7.310 0.334 2 31 Biosynthesis of amino acids
KEGG KEGG:00130 0.04241 33.111 0.043 1 4 Ubiquinone and other terpenoid-quinone biosynthesis
GO: Biological process GO:0006733 0.00035 32.009 0.153 3 17 oxidoreduction coenzyme metabolic process
GO: Biological process GO:0006098 0.00073 89.333 0.045 2 5 pentose-phosphate shunt
GO: Biological process GO:0006081 0.00073 89.333 0.045 2 5 cellular aldehyde metabolic process
GO: Biological process GO:0072524 0.00546 24.202 0.117 2 13 pyridine-containing compound metabolic process
GO: Biological process GO:0046496 0.00546 24.202 0.117 2 13 nicotinamide nucleotide metabolic process
GO: Biological process GO:0031032 0.00902 Inf 0.009 1 1 actomyosin structure organization
GO: Biological process GO:0051186 0.03134 8.886 0.288 2 35 cofactor metabolic process
GO: Biological process GO:0042181 0.03562 40.200 0.036 1 4 ketone biosynthetic process
GO: Biological process GO:0006108 0.03562 40.200 0.036 1 4 malate metabolic process
GO: Biological process GO:0006744 0.03562 40.200 0.036 1 4 ubiquinone biosynthetic process
GO: Biological process GO:1901661 0.03562 40.200 0.036 1 4 quinone metabolic process
GO: Biological process GO:0006979 0.03562 40.200 0.036 1 4 response to oxidative stress
GO: Biological process GO:0044281 0.04119 3.974 1.407 4 156 small molecule metabolic process
GO: Molecular function GO:0016491 0.00095 5.808 1.721 7 161 oxidoreductase activity
GO: Molecular function GO:0020037 0.00917 16.939 0.150 2 14 heme binding
GO: Molecular function GO:0008169 0.01069 Inf 0.011 1 1 C-methyltransferase activity
GO: Molecular function GO:0004054 0.01069 Inf 0.011 1 1 arginine kinase activity
GO: Molecular function GO:0004801 0.01069 Inf 0.011 1 1 sedoheptulose-7-phosphate:D-glyceraldehyde-3-phosphate glyceronetransferase activity
GO: Molecular function GO:0008425 0.01069 Inf 0.011 1 1 2-polyprenyl-6-methoxy-1,4-benzoquinone methyltransferase activity
GO: Molecular function GO:0004784 0.02128 97.100 0.021 1 2 superoxide dismutase activity
GO: Molecular function GO:0031177 0.02128 97.100 0.021 1 2 phosphopantetheine binding
GO: Molecular function GO:0004471 0.02128 97.100 0.021 1 2 malate dehydrogenase (decarboxylating) (NAD+) activity
GO: Molecular function GO:0004616 0.02128 97.100 0.021 1 2 phosphogluconate dehydrogenase (decarboxylating) activity
GO: Molecular function GO:0016615 0.04212 32.333 0.043 1 4 malate dehydrogenase activity
GO: Molecular function GO:0004601 0.04212 32.333 0.043 1 4 peroxidase activity
GO: Cellular component GO:0042600 0.00457 Inf 0.005 1 1 chorion
GO: Cellular component GO:0005737 0.03792 5.122 1.458 4 319 cytoplasm
GO: Cellular component GO:0005839 0.04048 31.604 0.041 1 9 proteasome core complex

KEGG and GO enrichment for differentially spliced genes

KEGG and GO enrichment for A. mellifera genes showing pheromone-modulated alternative splicing

# The gene universe is defined as all genes that have 2 or more isoforms. It would be anti-conservative if we instead included all genes, not just that are alternatively spliced
gene.universe.apis.splicing <- (tbl(my_db, "isoforms_am") %>% 
                                  group_by(gene) %>% 
                                  summarise(nIsoforms = n()) %>% filter(nIsoforms > 1) %>% 
                                  as.data.frame() %>% 
                                  dplyr::select(gene) %>% as.data.frame())[,1]

Table S22: Results of KEGG and GO enrichment analysis on the list of genes showing significant alternative splicing in A. mellifera. The gene universe was defined as all genes that showed alternative splicing in A. mellifera.

GO.and.KEGG.enrichment(am.alt.splice$Gene, gene.universe.apis.splicing) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04745 0.00580 24.049 0.122 2 11 Phototransduction - fly
KEGG KEGG:00564 0.04346 7.310 0.343 2 31 Glycerophospholipid metabolism
GO: Biological process GO:0007568 0.01189 Inf 0.012 1 1 aging
GO: Biological process GO:0032793 0.01189 Inf 0.012 1 1 positive regulation of CREB transcription factor activity
GO: Biological process GO:0090399 0.01189 Inf 0.012 1 1 replicative senescence
GO: Biological process GO:1901700 0.01189 Inf 0.012 1 1 response to oxygen-containing compound
GO: Biological process GO:0000723 0.01189 Inf 0.012 1 1 telomere maintenance
GO: Biological process GO:0010212 0.01189 Inf 0.012 1 1 response to ionizing radiation
GO: Biological process GO:0016572 0.01189 Inf 0.012 1 1 histone phosphorylation
GO: Biological process GO:1901031 0.01189 Inf 0.012 1 1 regulation of response to reactive oxygen species
GO: Biological process GO:0046470 0.01189 Inf 0.012 1 1 phosphatidylcholine metabolic process
GO: Biological process GO:0051103 0.02366 89.385 0.024 1 2 DNA ligation involved in DNA repair
GO: Biological process GO:0051090 0.02366 89.385 0.024 1 2 regulation of sequence-specific DNA binding transcription factor activity
GO: Biological process GO:0071897 0.02366 89.385 0.024 1 2 DNA biosynthetic process
GO: Biological process GO:0000075 0.02366 89.385 0.024 1 2 cell cycle checkpoint
GO: Biological process GO:0000077 0.02366 89.385 0.024 1 2 DNA damage checkpoint
GO: Biological process GO:0007049 0.03124 8.644 0.285 2 24 cell cycle
GO: Biological process GO:0007050 0.03529 44.654 0.036 1 3 cell cycle arrest
GO: Biological process GO:0080134 0.03529 44.654 0.036 1 3 regulation of response to stress
GO: Biological process GO:0033554 0.04442 7.012 0.345 2 29 cellular response to stress
GO: Biological process GO:0009628 0.04680 29.744 0.048 1 4 response to abiotic stimulus
GO: Biological process GO:0016569 0.04680 29.744 0.048 1 4 chromatin modification
GO: Biological process GO:0044093 0.04680 29.744 0.048 1 4 positive regulation of molecular function
GO: Molecular function GO:0001883 0.00254 3.828 3.916 10 355 purine nucleoside binding
GO: Molecular function GO:0032555 0.00254 3.828 3.916 10 355 purine ribonucleotide binding
GO: Molecular function GO:0032549 0.00260 3.815 3.927 10 356 ribonucleoside binding
GO: Molecular function GO:0005524 0.00299 3.912 3.309 9 300 ATP binding
GO: Molecular function GO:0030554 0.00306 3.897 3.320 9 301 adenyl nucleotide binding
GO: Molecular function GO:0097367 0.00421 3.529 4.181 10 379 carbohydrate derivative binding
GO: Molecular function GO:0000166 0.00670 3.175 5.218 11 473 nucleotide binding
GO: Molecular function GO:0004672 0.00971 4.535 1.368 5 124 protein kinase activity
GO: Molecular function GO:0005219 0.01103 Inf 0.011 1 1 ryanodine-sensitive calcium-release channel activity
GO: Molecular function GO:0060072 0.01103 Inf 0.011 1 1 large conductance calcium-activated potassium channel activity
GO: Molecular function GO:0004683 0.01103 Inf 0.011 1 1 calmodulin-dependent protein kinase activity
GO: Molecular function GO:0004622 0.01103 Inf 0.011 1 1 lysophospholipase activity
GO: Molecular function GO:0016772 0.01394 3.624 2.085 6 189 transferase activity, transferring phosphorus-containing groups
GO: Molecular function GO:0042626 0.02153 10.241 0.232 2 21 ATPase activity, coupled to transmembrane movement of substances
GO: Molecular function GO:0005227 0.02195 93.682 0.022 1 2 calcium activated cation channel activity
GO: Molecular function GO:0005217 0.02195 93.682 0.022 1 2 intracellular ligand-gated ion channel activity
GO: Molecular function GO:0099604 0.02195 93.682 0.022 1 2 ligand-gated calcium channel activity
GO: Molecular function GO:0003910 0.02195 93.682 0.022 1 2 DNA ligase (ATP) activity
GO: Molecular function GO:0015399 0.02352 9.724 0.243 2 22 primary active transmembrane transporter activity
GO: Molecular function GO:1901363 0.02650 2.469 8.946 14 811 heterocyclic compound binding
GO: Molecular function GO:0097159 0.02680 2.464 8.957 14 812 organic cyclic compound binding
GO: Molecular function GO:0016886 0.03275 46.818 0.033 1 3 ligase activity, forming phosphoric ester bonds
GO: Molecular function GO:0008440 0.04343 31.197 0.044 1 4 inositol-1,4,5-trisphosphate 3-kinase activity
GO: Cellular component GO:0043292 0.01958 106.875 0.020 1 2 contractile fiber
GO: Cellular component GO:0005861 0.01958 106.875 0.020 1 2 troponin complex
GO: Cellular component GO:0036379 0.01958 106.875 0.020 1 2 myofilament
GO: Cellular component GO:0030017 0.01958 106.875 0.020 1 2 sarcomere

KEGG and GO enrichment for L. flavus genes showing pheromone-modulated alternative splicing

# For flavus and niger, we additionally have to find the best BLAST Apis genes when constructing the gene lists
gene.universe.flavus.splicing <- (tbl(my_db, "isoforms_lf") %>% 
                                  group_by(gene) %>% 
                                  summarise(nIsoforms = n()) %>% filter(nIsoforms > 1) %>% 
                                  as.data.frame() %>% 
                                  dplyr::select(gene) %>% as.data.frame())[,1]

gene.universe.flavus.splicing <- (tbl(my_db, "lf2am") %>%  # Convert to Apis gene names via BLAST
                         filter(lf %in% gene.universe.flavus.splicing) %>% 
                         dplyr::select(am) %>% filter(!is.na(am)) %>% as.data.frame())[,1]

alt.spliced.flavus <- (tbl(my_db, "lf2am") %>% 
                         filter(lf %in% lf.alt.splice$Gene) %>% 
                         dplyr::select(am) %>% filter(!is.na(am)) %>% as.data.frame())[,1]

Table S23: Results of KEGG and GO enrichment analysis on the list of genes showing significant alternative splicing in L. flavus. The gene universe was defined as all genes that showed alternative splicing in L. flavus, which also had a known ortholog in A. mellifera.

GO.and.KEGG.enrichment(alt.spliced.flavus, gene.universe.flavus)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:01230 0.01331 14.889 0.185 2 35 Biosynthesis of amino acids
KEGG KEGG:01100 0.01420 6.619 2.514 6 476 Metabolic pathways
KEGG KEGG:01200 0.03367 8.800 0.301 2 57 Carbon metabolism
KEGG KEGG:00670 0.03645 35.738 0.037 1 7 One carbon pool by folate
KEGG KEGG:00061 0.04157 30.612 0.042 1 8 Fatty acid biosynthesis
GO: Biological process GO:0046483 0.00305 6.729 3.156 8 455 heterocycle metabolic process
GO: Biological process GO:0006725 0.00309 6.708 3.163 8 456 cellular aromatic compound metabolic process
GO: Biological process GO:1901360 0.00329 6.625 3.190 8 460 organic cyclic compound metabolic process
GO: Biological process GO:0051187 0.00694 Inf 0.007 1 1 cofactor catabolic process
GO: Biological process GO:0003012 0.00694 Inf 0.007 1 1 muscle system process
GO: Biological process GO:0006788 0.00694 Inf 0.007 1 1 heme oxidation
GO: Biological process GO:0006937 0.00694 Inf 0.007 1 1 regulation of muscle contraction
GO: Biological process GO:0033015 0.00694 Inf 0.007 1 1 tetrapyrrole catabolic process
GO: Biological process GO:0032264 0.00694 Inf 0.007 1 1 IMP salvage
GO: Biological process GO:0009126 0.01298 14.361 0.180 2 26 purine nucleoside monophosphate metabolic process
GO: Biological process GO:0035999 0.01383 157.400 0.014 1 2 tetrahydrofolate interconversion
GO: Biological process GO:0044057 0.01383 157.400 0.014 1 2 regulation of system process
GO: Biological process GO:0009161 0.01712 12.278 0.208 2 30 ribonucleoside monophosphate metabolic process
GO: Biological process GO:0006163 0.01823 11.847 0.215 2 31 purine nucleotide metabolic process
GO: Biological process GO:0006760 0.02068 78.650 0.021 1 3 folic acid-containing compound metabolic process
GO: Biological process GO:0006544 0.02068 78.650 0.021 1 3 glycine metabolic process
GO: Biological process GO:0043101 0.02068 78.650 0.021 1 3 purine-containing compound salvage
GO: Biological process GO:0009259 0.02297 10.384 0.243 2 35 ribonucleotide metabolic process
GO: Biological process GO:0008152 0.02409 7.138 6.443 10 929 metabolic process
GO: Biological process GO:2001141 0.02555 5.908 0.673 3 97 regulation of RNA biosynthetic process
GO: Biological process GO:0006355 0.02555 5.908 0.673 3 97 regulation of transcription, DNA-templated
GO: Biological process GO:0006165 0.02748 52.400 0.028 1 4 nucleoside diphosphate phosphorylation
GO: Biological process GO:0006563 0.02748 52.400 0.028 1 4 L-serine metabolic process
GO: Biological process GO:0046040 0.02748 52.400 0.028 1 4 IMP metabolic process
GO: Biological process GO:0006096 0.02748 52.400 0.028 1 4 glycolytic process
GO: Biological process GO:0043173 0.02748 52.400 0.028 1 4 nucleotide salvage
GO: Biological process GO:0019219 0.02770 5.714 0.694 3 100 regulation of nucleobase-containing compound metabolic process
GO: Biological process GO:0051186 0.03084 8.884 0.285 2 45 cofactor metabolic process
GO: Biological process GO:0006778 0.03424 39.275 0.035 1 5 porphyrin-containing compound metabolic process
GO: Biological process GO:0009889 0.03640 5.094 0.770 3 111 regulation of biosynthetic process
GO: Biological process GO:0009185 0.04096 31.400 0.042 1 6 ribonucleoside diphosphate metabolic process
GO: Biological process GO:0009135 0.04096 31.400 0.042 1 6 purine nucleoside diphosphate metabolic process
GO: Biological process GO:0046031 0.04096 31.400 0.042 1 6 ADP metabolic process
GO: Biological process GO:0016052 0.04096 31.400 0.042 1 6 carbohydrate catabolic process
GO: Biological process GO:0060255 0.04546 4.630 0.839 3 121 regulation of macromolecule metabolic process
GO: Biological process GO:0042440 0.04764 26.150 0.049 1 7 pigment metabolic process
GO: Biological process GO:0034641 0.04855 3.298 3.835 7 553 cellular nitrogen compound metabolic process
GO: Molecular function GO:0004392 0.00539 Inf 0.005 1 1 heme oxygenase (decyclizing) activity
GO: Molecular function GO:0004372 0.00539 Inf 0.005 1 1 glycine hydroxymethyltransferase activity
GO: Molecular function GO:0004332 0.00539 Inf 0.005 1 1 fructose-bisphosphate aldolase activity
GO: Molecular function GO:0003876 0.00539 Inf 0.005 1 1 AMP deaminase activity
GO: Molecular function GO:0031177 0.01075 198.692 0.011 1 2 phosphopantetheine binding
GO: Molecular function GO:0019239 0.01609 99.308 0.016 1 3 deaminase activity
GO: Molecular function GO:0004181 0.01609 99.308 0.016 1 3 metallocarboxypeptidase activity
GO: Molecular function GO:0016814 0.02139 66.179 0.022 1 4 hydrolase activity, acting on carbon-nitrogen (but not peptide) bonds, in cyclic amidines
GO: Molecular function GO:0004402 0.02139 66.179 0.022 1 4 histone acetyltransferase activity
GO: Molecular function GO:0034212 0.02668 49.615 0.027 1 5 peptide N-acetyltransferase activity
GO: Molecular function GO:0003690 0.02668 49.615 0.027 1 5 double-stranded DNA binding
GO: Cellular component GO:0043292 0.00845 264.625 0.008 1 2 contractile fiber
GO: Cellular component GO:0005861 0.00845 264.625 0.008 1 2 troponin complex
GO: Cellular component GO:0036379 0.00845 264.625 0.008 1 2 myofilament
GO: Cellular component GO:0030017 0.00845 264.625 0.008 1 2 sarcomere
GO: Cellular component GO:0005681 0.03751 32.969 0.038 1 9 spliceosomal complex

KEGG and GO enrichment for L. niger genes showing pheromone-modulated alternative splicing

gene.universe.niger.splicing <- (tbl(my_db, "isoforms_ln") %>% 
                                  group_by(gene) %>% 
                                  summarise(nIsoforms = n()) %>% filter(nIsoforms > 1) %>% 
                                  as.data.frame() %>% 
                                  dplyr::select(gene) %>% as.data.frame())[,1]

gene.universe.niger.splicing <- (tbl(my_db, "ln2am") %>%  # Convert to Apis gene names via BLAST
                         filter(ln %in% gene.universe.niger.splicing) %>% 
                         dplyr::select(am) %>% filter(!is.na(am)) %>% as.data.frame())[,1] %>%
  unique

alt.spliced.niger <- (tbl(my_db, "ln2am") %>% 
                        filter(ln %in% ln.alt.splice$Gene) %>% 
                        dplyr::select(am)%>% filter(!is.na(am)) %>% as.data.frame())[,1]

Table S24: Results of KEGG and GO enrichment analysis on the list of genes showing significant alternative splicing in L. niger. The gene universe was defined as all genes that showed alternative splicing in L. niger, which also had a known ortholog in A. mellifera.

GO.and.KEGG.enrichment(alt.spliced.niger, gene.universe.niger.splicing) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:00760 0.00495 27.000 0.113 2 7 Nicotinate and nicotinamide metabolism
KEGG KEGG:04745 0.00832 19.254 0.145 2 9 Phototransduction - fly
KEGG KEGG:00630 0.02003 11.185 0.226 2 14 Glyoxylate and dicarboxylate metabolism
KEGG KEGG:04391 0.04708 6.667 0.355 2 22 Hippo signaling pathway - fly
GO: Biological process GO:0019363 0.00237 45.193 0.080 2 5 pyridine nucleotide biosynthetic process
GO: Biological process GO:0072524 0.01463 13.484 0.192 2 12 pyridine-containing compound metabolic process
GO: Biological process GO:0035999 0.01601 Inf 0.016 1 1 tetrahydrofolate interconversion
GO: Biological process GO:0072583 0.01601 Inf 0.016 1 1 clathrin-dependent endocytosis
GO: Biological process GO:0035023 0.01978 11.219 0.224 2 14 regulation of Rho protein signal transduction
GO: Biological process GO:0051186 0.02548 5.496 0.656 3 41 cofactor metabolic process
GO: Biological process GO:0006733 0.02559 9.602 0.256 2 16 oxidoreduction coenzyme metabolic process
GO: Biological process GO:0019674 0.03031 67.842 0.031 1 2 NAD metabolic process
GO: Biological process GO:0006760 0.03177 64.500 0.032 1 2 folic acid-containing compound metabolic process
GO: Biological process GO:0006741 0.03177 64.500 0.032 1 2 NADP biosynthetic process
GO: Biological process GO:0009435 0.03177 64.500 0.032 1 2 NAD biosynthetic process
GO: Biological process GO:0006563 0.03177 64.500 0.032 1 2 L-serine metabolic process
GO: Biological process GO:0007205 0.03177 64.500 0.032 1 2 protein kinase C-activating G-protein coupled receptor signaling pathway
GO: Biological process GO:0007265 0.04268 7.047 0.336 2 21 Ras protein signal transduction
GO: Biological process GO:0006544 0.04729 32.225 0.048 1 3 glycine metabolic process
GO: Molecular function GO:0005093 0.01869 Inf 0.019 1 1 Rab GDP-dissociation inhibitor activity
GO: Molecular function GO:0004054 0.01869 Inf 0.019 1 1 arginine kinase activity
GO: Molecular function GO:0004791 0.01869 Inf 0.019 1 1 thioredoxin-disulfide reductase activity
GO: Molecular function GO:0005391 0.01869 Inf 0.019 1 1 sodium:potassium-exchanging ATPase activity
GO: Molecular function GO:0003952 0.01869 Inf 0.019 1 1 NAD+ synthase (glutamine-hydrolyzing) activity
GO: Molecular function GO:0004372 0.01869 Inf 0.019 1 1 glycine hydroxymethyltransferase activity
GO: Molecular function GO:0005089 0.03068 8.449 0.280 2 15 Rho guanyl-nucleotide exchange factor activity
GO: Molecular function GO:0008237 0.03248 4.784 0.710 3 38 metallopeptidase activity
GO: Molecular function GO:0043167 0.03462 1.956 9.495 15 508 ion binding
GO: Molecular function GO:0004890 0.03704 53.821 0.037 1 2 GABA-A receptor activity
GO: Molecular function GO:0003994 0.03704 53.821 0.037 1 2 aconitate hydratase activity
GO: Molecular function GO:0003951 0.03704 53.821 0.037 1 2 NAD+ kinase activity
GO: Molecular function GO:0004143 0.03704 53.821 0.037 1 2 diacylglycerol kinase activity
GO: Cellular component GO:0005868 0.01476 Inf 0.015 1 1 cytoplasmic dynein complex

Figures summarising KEGG and GO results

These two figures help to see which KEGG and GO terms showed up more than once, and to compare Apis and the two Lasius species.

# First, look for enriched KEGG and GO terms in all the DE gene and isoform lists jsut as before, but this time return all the results (keep.all = TRUE)
big.table <- rbind(suppressMessages(
  GO.and.KEGG.enrichment(up.in.control.apis, gene.universe.apis, kable = FALSE, keep.all = TRUE) ) %>% 
    mutate(species = "A. mellifera", type = "Up in control"),
  GO.and.KEGG.enrichment(up.in.QP.apis, gene.universe.apis, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "A. mellifera", type = "Up in QP"),
  GO.and.KEGG.enrichment(up.in.control.flavus, gene.universe.flavus, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. flavus", type = "Up in control"),
  GO.and.KEGG.enrichment(up.in.QP.flavus, gene.universe.flavus, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. flavus", type = "Up in QP"),
  GO.and.KEGG.enrichment(up.in.control.niger, gene.universe.niger, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. niger", type = "Up in control"),
  GO.and.KEGG.enrichment(up.in.QP.niger, gene.universe.niger, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. niger", type = "Up in QP"),
  GO.and.KEGG.enrichment(am.alt.splice$Gene, gene.universe.apis.splicing,  kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "A. mellifera", type = "Splicing"),
  GO.and.KEGG.enrichment(alt.spliced.flavus, gene.universe.flavus, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. flavus", type = "Splicing"),
  GO.and.KEGG.enrichment(alt.spliced.niger, gene.universe.niger.splicing, kable = FALSE, keep.all = TRUE) %>% 
    mutate(species = "L. niger", type = "Splicing")) %>% 
  filter(Test_type %in% c("KEGG", "GO: Biological process"))

# This line means that GO/KEGG categories which did not even appear in the list of enriched genes get a p value of 1 
plot.data <- expand.grid(ID = unique(big.table$ID), 
                         species = unique(big.table$species), 
                         type = unique(big.table$type), stringsAsFactors = FALSE) %>% 
  left_join(big.table %>% dplyr::select(ID, type, species, Pvalue), by = c("ID", "species", "type")) %>% 
  mutate(Pvalue = as.numeric(as.character(replace(Pvalue, is.na(Pvalue), 1)))) 

Summary figure of KEGG results

Figure 2: A summary of the KEGG enrichment tests: KEGG terms with multiple red squares were significantly enriched in multiple tests. Each square shows one of three results, for one of three species, and the colour of the square indicates the p-value for that result (on a -log10 scale) - blue squares are not statistically significant, red squares are significant (and are also marked with asterisks), and white squares are close to the p = 0.05 threshold. The “Up in QP” rows show the results of enrichment tests for KEGG terms on the gene set that was significantly up-regulated in queen pheromone-treated workers. The “Up in control” row shows the same tests, on the gene set that was significantly up-regulated in control workers. The “Splicing” row shows the results of the same tests, on the gene set that showed a significant change in alterative splicing between the two treatments.

kegg.plot.data <- plot.data %>% filter(grepl("KEGG", ID))
kegg.plot.data <- kegg.plot.data[kegg.plot.data$ID %in% (kegg.plot.data %>% 
                                            group_by(ID) %>% 
                                            summarise(min.p = min(Pvalue)) %>% 
                                            filter(min.p < 0.05) %>% .$ID), ] %>% 
  left_join(big.table %>% select(ID, Term), by = "ID") %>% 
  distinct() %>% mutate(sig = " ", sig = replace(sig, Pvalue<0.05, "*"))

kegg.plot <- kegg.plot.data %>% ggplot(aes(x = species, y = type, fill = -log10(Pvalue+0.000000001))) + 
  geom_tile(colour="black") +
  geom_text(aes(label=sig)) +
  facet_wrap(~Term, labeller = labeller(Term = label_wrap_gen(30))) + 
  scale_fill_gradient2(name = "-log10(p)", low = "steelblue", mid = "white", high = "tomato", midpoint = -log10(0.05)) + 
  theme_bw() + scale_x_discrete(expand=c(0,0)) + scale_y_discrete(expand=c(0,0)) + 
  theme(panel.grid = element_blank(), 
        strip.background = element_rect(fill = "white"), 
        axis.text.x = element_text(face = "italic"),
        legend.position = c(12/14, 1/12), legend.direction = "horizontal") + 
  xlab(NULL) + ylab(NULL)
ggsave(kegg.plot, file = "figures/KEGG summary fig.pdf", height = 8, width = 12)
kegg.plot

Summary figure of GO results

Figure 3: A summary of the GO enrichment tests: GO terms with multiple red squares were significantly enriched in multiple tests. For brevity, the figure only shows GO terms for which two or more enrichment tests returned a significant result. The figure can be interpreted as for Figure S7.

go.plot.data <- plot.data %>% filter(grepl("GO", ID))
go.plot.data <- go.plot.data[go.plot.data$ID %in% (go.plot.data %>% 
                                                     group_by(ID) %>% 
                                                     summarise(n.sig = sum(Pvalue<0.05)) %>% 
                                                     filter(n.sig >1) %>% .$ID), ] %>% 
  left_join(big.table %>% select(ID, Term), by = "ID") %>% distinct() %>% 
  mutate(sig = " ", sig = replace(sig, Pvalue<0.05, "*"))
go.plot.data$Term <- with(go.plot.data, paste(toupper(substr(Term, 1, 1)), substr(Term, 2, nchar(Term)), sep=""))

go.plot <- go.plot.data %>% 
  filter(Term != "Purine nucleoside monophosphate metabolic process", # omit these 'child' GO terms for brevity
         Term != "Purine nucleoside diphosphate metabolic process",
         Term != "Purine nucleoside triphosphate metabolic process",
         Term != "Ribonucleoside monophosphate metabolic process",
         Term != "Ribonucleoside diphosphate metabolic process",
         Term != "Ribonucleoside triphosphate metabolic process") %>%
  ggplot(aes(x = species, y = type, fill = -log10(Pvalue + 0.000000001))) + 
  geom_tile(colour="black") +
  geom_text(aes(label=sig)) +
  facet_wrap(~Term, labeller = labeller(Term = label_wrap_gen(25))) + 
  scale_fill_gradient2(name = "-log10(p)", low = "steelblue", mid = "white", high = "tomato", midpoint = -log10(0.05)) + 
  theme_bw() + scale_x_discrete(expand=c(0,0)) + scale_y_discrete(expand=c(0,0)) + 
  theme(panel.grid = element_blank(), 
        strip.background = element_rect(fill = "white"), 
        axis.text.x = element_text(face = "italic"),
        legend.position = c(12/14, 1/12), legend.direction = "horizontal") + 
  xlab(NULL) + ylab(NULL)
ggsave(go.plot, file = "figures/GO summary fig.pdf", height = 10, width = 13)
go.plot

KEGG and GO enrichment for transcriptional modules

Enriched KEGG and GO terms in module 1

Table S25: Results of KEGG and GO enrichment analysis for the genes in Module 1. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(1), gene.universe.modules)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:03440 0.00028 15.874 6.389 13 14 Homologous recombination
KEGG KEGG:03460 0.00119 13.377 5.477 11 12 Fanconi anemia pathway
KEGG KEGG:03420 0.00453 6.677 5.933 11 13 Nucleotide excision repair
KEGG KEGG:03040 0.00897 2.075 23.275 32 51 Spliceosome
KEGG KEGG:03430 0.01946 8.443 3.651 7 8 Mismatch repair
GO: Biological process GO:0090304 0.00000 2.022 118.799 153 256 nucleic acid metabolic process
GO: Biological process GO:0033554 0.00029 3.901 15.778 26 34 cellular response to stress
GO: Biological process GO:0006281 0.00036 4.106 14.386 24 31 DNA repair
GO: Biological process GO:0044260 0.00050 1.521 192.120 219 414 cellular macromolecule metabolic process
GO: Biological process GO:0006396 0.00147 2.556 22.393 33 49 RNA processing
GO: Biological process GO:0046483 0.00159 1.488 153.139 176 330 heterocycle metabolic process
GO: Biological process GO:1901360 0.00193 1.475 154.531 177 333 organic cyclic compound metabolic process
GO: Biological process GO:0006725 0.00295 1.450 153.603 175 331 cellular aromatic compound metabolic process
GO: Biological process GO:0006397 0.00372 3.119 13.458 21 29 mRNA processing
GO: Biological process GO:0016043 0.00483 1.819 41.765 54 90 cellular component organization
GO: Biological process GO:0051276 0.00958 Inf 2.773 6 6 chromosome organization
GO: Biological process GO:0009968 0.02130 Inf 2.320 5 5 negative regulation of signal transduction
GO: Biological process GO:0006310 0.02130 Inf 2.320 5 5 DNA recombination
GO: Biological process GO:0006399 0.02270 2.168 15.778 22 34 tRNA metabolic process
GO: Biological process GO:0016192 0.02379 1.875 22.739 30 49 vesicle-mediated transport
GO: Biological process GO:0009987 0.03746 1.320 347.536 360 769 cellular process
GO: Biological process GO:0000280 0.04161 7.000 3.248 6 7 nuclear division
GO: Biological process GO:0061025 0.04161 7.000 3.248 6 7 membrane fusion
GO: Biological process GO:0071103 0.04608 Inf 1.856 4 4 DNA conformation change
GO: Biological process GO:0043161 0.04608 Inf 1.856 4 4 proteasome-mediated ubiquitin-dependent protein catabolic process
GO: Biological process GO:0098813 0.04608 Inf 1.856 4 4 nuclear chromosome segregation
GO: Biological process GO:0000070 0.04608 Inf 1.856 4 4 mitotic sister chromatid segregation
GO: Biological process GO:0000075 0.04608 Inf 1.856 4 4 cell cycle checkpoint
GO: Biological process GO:0051304 0.04608 Inf 1.856 4 4 chromosome separation
GO: Biological process GO:0019941 0.04718 1.963 14.850 20 32 modification-dependent protein catabolic process
GO: Biological process GO:0006807 0.04937 1.235 205.114 219 442 nitrogen compound metabolic process
GO: Molecular function GO:0003676 0.00001 1.676 167.146 205 377 nucleic acid binding
GO: Molecular function GO:0008270 0.00173 1.649 70.937 89 160 zinc ion binding
GO: Molecular function GO:0005096 0.00177 7.636 6.207 12 14 GTPase activator activity
GO: Molecular function GO:0016811 0.00389 11.421 4.434 9 10 hydrolase activity, acting on carbon-nitrogen (but not peptide) bonds, in linear amides
GO: Molecular function GO:0030554 0.00459 1.448 107.736 127 243 adenyl nucleotide binding
GO: Molecular function GO:0005524 0.00566 1.435 107.293 126 242 ATP binding
GO: Molecular function GO:0016740 0.00648 1.383 133.007 153 300 transferase activity
GO: Molecular function GO:0008276 0.00751 Inf 2.660 6 6 protein methyltransferase activity
GO: Molecular function GO:0060589 0.00903 3.562 8.424 14 19 nucleoside-triphosphatase regulator activity
GO: Molecular function GO:0016779 0.01553 2.547 11.971 18 27 nucleotidyltransferase activity
GO: Molecular function GO:0000166 0.01637 1.281 182.664 202 412 nucleotide binding
GO: Molecular function GO:0008242 0.01701 Inf 2.217 5 5 omega peptidase activity
GO: Molecular function GO:0016278 0.01701 Inf 2.217 5 5 lysine N-methyltransferase activity
GO: Molecular function GO:0004725 0.01772 4.227 5.764 10 13 protein tyrosine phosphatase activity
GO: Molecular function GO:0035091 0.02205 3.488 6.650 11 15 phosphatidylinositol binding
GO: Molecular function GO:0008080 0.02447 5.064 4.434 8 10 N-acetyltransferase activity
GO: Molecular function GO:0046872 0.02640 1.257 174.683 192 394 metal ion binding
GO: Molecular function GO:1901363 0.03293 1.275 137.137 152 330 heterocyclic compound binding
GO: Molecular function GO:0097159 0.03293 1.275 137.137 152 330 organic cyclic compound binding
GO: Molecular function GO:0036459 0.03762 3.167 6.207 10 14 thiol-dependent ubiquitinyl hydrolase activity
GO: Molecular function GO:0018024 0.03847 Inf 1.773 4 4 histone-lysine N-methyltransferase activity
GO: Molecular function GO:0003690 0.03847 Inf 1.773 4 4 double-stranded DNA binding
GO: Molecular function GO:0004386 0.04042 2.080 12.857 18 29 helicase activity
GO: Molecular function GO:0016875 0.04266 2.788 7.094 11 16 ligase activity, forming carbon-oxygen bonds
GO: Molecular function GO:0004812 0.04266 2.788 7.094 11 16 aminoacyl-tRNA ligase activity
GO: Molecular function GO:0004672 0.04337 1.550 32.365 40 73 protein kinase activity
GO: Cellular component GO:0005623 0.00008 1.529 319.265 354 776 cell
GO: Cellular component GO:0043227 0.00072 1.496 146.879 173 357 membrane-bounded organelle
GO: Cellular component GO:0005681 0.00080 Inf 3.291 8 8 spliceosomal complex
GO: Cellular component GO:0005634 0.00262 1.592 71.381 89 179 nucleus
GO: Cellular component GO:0005622 0.00263 1.773 45.593 60 124 intracellular
GO: Cellular component GO:0043229 0.00292 1.384 189.667 214 461 intracellular organelle
GO: Cellular component GO:0000151 0.01004 10.126 3.291 7 8 ubiquitin ligase complex
GO: Cellular component GO:0044428 0.01102 1.930 23.117 32 57 nuclear part
GO: Cellular component GO:0005694 0.01119 Inf 2.040 5 5 chromosome
GO: Cellular component GO:0044424 0.01126 1.570 50.614 63 132 intracellular part
GO: Cellular component GO:0043234 0.01314 1.433 78.399 93 192 protein complex
GO: Cellular component GO:0005875 0.02123 3.623 5.760 10 14 microtubule associated complex
GO: Cellular component GO:0000228 0.02916 5.057 3.703 7 9 nuclear chromosome
GO: Cellular component GO:0044427 0.04213 2.655 6.994 11 17 chromosomal part
GO: Cellular component GO:0031011 0.04612 7.207 2.469 5 6 Ino80 complex
GO: Cellular component GO:0044422 0.04686 1.314 79.816 91 194 organelle part

Enriched KEGG and GO terms in module 2

Table S26: Results of KEGG and GO enrichment analysis for the genes in Module 2. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(2), gene.universe.modules)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:03010 0.00000 13.284 12.037 43 58 Ribosome
KEGG KEGG:03050 0.00426 3.170 5.603 12 27 Proteasome
KEGG KEGG:00051 0.00538 9.740 1.453 5 7 Fructose and mannose metabolism
KEGG KEGG:00590 0.00759 15.532 1.038 4 5 Arachidonic acid metabolism
KEGG KEGG:04150 0.04175 2.048 7.264 12 35 mTOR signaling pathway
GO: Biological process GO:0006518 0.00000 5.801 16.624 46 87 peptide metabolic process
GO: Biological process GO:0043604 0.00000 5.789 16.242 45 85 amide biosynthetic process
GO: Biological process GO:0006412 0.00000 5.370 15.548 42 82 translation
GO: Biological process GO:1901566 0.00000 3.395 27.134 56 142 organonitrogen compound biosynthetic process
GO: Biological process GO:0009059 0.00064 1.798 43.949 62 230 macromolecule biosynthetic process
GO: Biological process GO:0018193 0.00281 6.097 2.293 7 12 peptidyl-amino acid modification
GO: Biological process GO:0044249 0.01080 1.484 58.911 73 312 cellular biosynthetic process
GO: Biological process GO:0034641 0.02782 1.367 76.433 89 400 cellular nitrogen compound metabolic process
GO: Biological process GO:0071704 0.02957 1.362 120.382 133 630 organic substance metabolic process
GO: Biological process GO:0006457 0.03428 2.443 4.777 9 25 protein folding
GO: Biological process GO:0044267 0.03616 1.674 15.210 22 93 cellular protein metabolic process
GO: Biological process GO:0006414 0.03637 Inf 0.382 2 2 translational elongation
GO: Biological process GO:0044205 0.03637 Inf 0.382 2 2 ‘de novo’ UMP biosynthetic process
GO: Biological process GO:0018095 0.03637 Inf 0.382 2 2 protein polyglutamylation
GO: Biological process GO:0044712 0.03981 2.752 3.439 7 18 single-organism catabolic process
GO: Biological process GO:0044238 0.04036 1.327 112.166 124 587 primary metabolic process
GO: Biological process GO:0044272 0.04783 4.296 1.529 4 8 sulfur compound biosynthetic process
GO: Molecular function GO:0003735 0.00000 13.498 9.757 40 56 structural constituent of ribosome
GO: Molecular function GO:0004298 0.00140 9.650 1.568 6 9 threonine-type endopeptidase activity
GO: Molecular function GO:0016491 0.00767 1.679 26.310 38 151 oxidoreductase activity
GO: Molecular function GO:0019843 0.01827 14.350 0.697 3 4 rRNA binding
GO: Molecular function GO:0016209 0.01832 4.802 1.742 5 10 antioxidant activity
GO: Molecular function GO:0050660 0.02528 3.064 3.136 7 18 flavin adenine dinucleotide binding
GO: Molecular function GO:0016635 0.03028 Inf 0.348 2 2 oxidoreductase activity, acting on the CH-CH group of donors, quinone or related compound as acceptor
GO: Molecular function GO:0052689 0.04262 3.425 2.091 5 12 carboxylic ester hydrolase activity
GO: Molecular function GO:0008135 0.04366 2.407 4.182 8 24 translation factor activity, RNA binding
GO: Cellular component GO:0005840 0.00000 11.975 10.542 41 60 ribosome
GO: Cellular component GO:1990904 0.00000 6.453 16.516 50 94 ribonucleoprotein complex
GO: Cellular component GO:0043228 0.00000 3.175 23.896 50 136 non-membrane-bounded organelle
GO: Cellular component GO:0005839 0.00146 9.595 1.581 6 9 proteasome core complex
GO: Cellular component GO:0015935 0.00146 9.595 1.581 6 9 small ribosomal subunit
GO: Cellular component GO:0005737 0.00261 2.129 14.512 25 99 cytoplasm
GO: Cellular component GO:0015934 0.00537 Inf 0.527 3 3 large ribosomal subunit
GO: Cellular component GO:1905369 0.00999 4.785 2.108 6 12 endopeptidase complex
GO: Cellular component GO:0043229 0.01555 1.387 81.000 96 461 intracellular organelle
GO: Cellular component GO:0005732 0.03077 Inf 0.351 2 2 small nucleolar ribonucleoprotein complex
GO: Cellular component GO:0005615 0.03620 4.753 1.406 4 8 extracellular space
GO: Cellular component GO:0044444 0.04860 1.509 20.765 28 136 cytoplasmic part

Enriched KEGG and GO terms in module 3

Table S27: Results of KEGG and GO enrichment analysis for the genes in Module 3. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(3), gene.universe.modules) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04080 0.00001 24.165 0.576 6 11 Neuroactive ligand-receptor interaction
KEGG KEGG:00020 0.00964 5.916 0.890 4 17 Citrate cycle (TCA cycle)
KEGG KEGG:00130 0.01509 18.727 0.209 2 4 Ubiquinone and other terpenoid-quinone biosynthesis
KEGG KEGG:01200 0.01696 3.351 2.146 6 41 Carbon metabolism
KEGG KEGG:04013 0.01961 3.720 1.623 5 31 MAPK signaling pathway - fly
KEGG KEGG:00350 0.02431 12.473 0.262 2 5 Tyrosine metabolism
GO: Biological process GO:0023052 0.00000 4.609 11.210 31 154 signaling
GO: Biological process GO:0044763 0.00000 3.199 29.517 50 414 single-organism cellular process
GO: Biological process GO:0050896 0.00000 3.298 14.195 31 195 response to stimulus
GO: Biological process GO:0050789 0.00000 3.052 19.727 38 271 regulation of biological process
GO: Biological process GO:0035556 0.00001 4.078 7.061 20 97 intracellular signal transduction
GO: Biological process GO:0007265 0.00021 8.047 1.383 7 19 Ras protein signal transduction
GO: Biological process GO:0051056 0.00030 7.420 1.456 7 20 regulation of small GTPase mediated signal transduction
GO: Biological process GO:0007218 0.00037 Inf 0.218 3 3 neuropeptide signaling pathway
GO: Biological process GO:0009966 0.00068 5.280 2.111 8 29 regulation of signal transduction
GO: Biological process GO:0007165 0.00131 4.149 2.841 9 48 signal transduction
GO: Biological process GO:0035023 0.00146 8.425 0.946 5 13 regulation of Rho protein signal transduction
GO: Biological process GO:0007267 0.02266 6.578 0.655 3 9 cell-cell signaling
GO: Biological process GO:0099537 0.02852 13.038 0.291 2 4 trans-synaptic signaling
GO: Biological process GO:0006836 0.02852 13.038 0.291 2 4 neurotransmitter transport
GO: Biological process GO:0007268 0.02852 13.038 0.291 2 4 chemical synaptic transmission
GO: Biological process GO:0006099 0.03070 5.633 0.728 3 10 tricarboxylic acid cycle
GO: Biological process GO:0008219 0.04531 8.684 0.364 2 5 cell death
GO: Biological process GO:0006915 0.04531 8.684 0.364 2 5 apoptotic process
GO: Molecular function GO:0015267 0.00000 17.267 2.176 14 22 channel activity
GO: Molecular function GO:0005216 0.00000 17.267 2.176 14 22 ion channel activity
GO: Molecular function GO:0060089 0.00000 6.818 5.440 22 55 molecular transducer activity
GO: Molecular function GO:0038023 0.00000 6.199 4.649 18 47 signaling receptor activity
GO: Molecular function GO:0005230 0.00000 38.171 0.989 8 10 extracellular ligand-gated ion channel activity
GO: Molecular function GO:0022891 0.00002 3.691 6.924 19 70 substrate-specific transmembrane transporter activity
GO: Molecular function GO:0005215 0.00004 2.893 11.078 25 112 transporter activity
GO: Molecular function GO:0005234 0.00009 Inf 0.396 4 4 extracellular-glutamate-gated ion channel activity
GO: Molecular function GO:0004970 0.00009 Inf 0.396 4 4 ionotropic glutamate receptor activity
GO: Molecular function GO:0022835 0.00009 Inf 0.396 4 4 transmitter-gated channel activity
GO: Molecular function GO:0099600 0.00029 4.429 3.415 11 36 transmembrane receptor activity
GO: Molecular function GO:0004930 0.00037 5.352 2.473 9 25 G-protein coupled receptor activity
GO: Molecular function GO:0004889 0.00095 Inf 0.297 3 3 acetylcholine-activated cation-selective channel activity
GO: Molecular function GO:0022834 0.00109 19.085 0.581 4 6 ligand-gated channel activity
GO: Molecular function GO:0005267 0.00118 18.631 0.593 4 6 potassium channel activity
GO: Molecular function GO:0005085 0.00287 4.706 2.077 7 21 guanyl-nucleotide exchange factor activity
GO: Molecular function GO:0005089 0.00595 5.835 1.286 5 13 Rho guanyl-nucleotide exchange factor activity
GO: Molecular function GO:0048038 0.00973 Inf 0.198 2 2 quinone binding
GO: Molecular function GO:0015291 0.01205 6.194 0.989 4 10 secondary active transmembrane transporter activity
GO: Molecular function GO:0046873 0.01317 3.740 2.077 6 21 metal ion transmembrane transporter activity
GO: Molecular function GO:0015294 0.01519 9.254 0.593 3 6 solute:cation symporter activity
GO: Molecular function GO:0005509 0.01607 2.484 4.748 10 48 calcium ion binding
GO: Molecular function GO:0042302 0.01750 5.306 1.088 4 11 structural constituent of cuticle
GO: Molecular function GO:0005328 0.02729 18.424 0.297 2 3 neurotransmitter:sodium symporter activity
GO: Molecular function GO:0016849 0.03665 5.546 0.791 3 8 phosphorus-oxygen lyase activity
GO: Molecular function GO:0004857 0.03665 5.546 0.791 3 8 enzyme inhibitor activity
GO: Molecular function GO:0019887 0.03665 5.546 0.791 3 8 protein kinase regulator activity
GO: Molecular function GO:0015077 0.03686 2.796 2.572 6 26 monovalent inorganic cation transmembrane transporter activity
GO: Molecular function GO:0008324 0.04009 2.305 3.998 8 41 cation transmembrane transporter activity
GO: Molecular function GO:0004674 0.04050 3.098 1.978 5 20 protein serine/threonine kinase activity
GO: Cellular component GO:0044456 0.00000 Inf 0.776 7 7 synapse part
GO: Cellular component GO:0045211 0.00000 Inf 0.785 7 7 postsynaptic membrane
GO: Cellular component GO:0098590 0.00000 58.034 0.897 7 8 plasma membrane region
GO: Cellular component GO:0030054 0.00000 22.222 1.233 8 11 cell junction
GO: Cellular component GO:0016021 0.00003 2.023 70.047 94 625 integral component of membrane
GO: Cellular component GO:0044425 0.00012 1.916 73.970 96 660 membrane part
GO: Cellular component GO:0098793 0.01249 Inf 0.224 2 2 presynapse
GO: Cellular component GO:0005886 0.01638 3.156 2.799 7 26 plasma membrane
GO: Cellular component GO:0005576 0.01871 2.329 5.604 11 50 extracellular region

Enriched KEGG and GO terms in module 4

Table S28: Results of KEGG and GO enrichment analysis for the genes in Module 4. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(4), gene.universe.modules) 
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04141 0.00000 4.973 7.152 22 59 Protein processing in endoplasmic reticulum
KEGG KEGG:01200 0.00003 4.591 4.970 15 41 Carbon metabolism
KEGG KEGG:01212 0.00014 6.929 2.303 9 19 Fatty acid metabolism
KEGG KEGG:01100 0.00084 1.857 41.455 58 342 Metabolic pathways
KEGG KEGG:01040 0.00094 29.875 0.606 4 5 Biosynthesis of unsaturated fatty acids
KEGG KEGG:01230 0.00094 4.276 3.394 10 28 Biosynthesis of amino acids
KEGG KEGG:00030 0.00141 7.548 1.455 6 12 Pentose phosphate pathway
KEGG KEGG:04512 0.00540 9.938 0.848 4 7 ECM-receptor interaction
KEGG KEGG:00061 0.00540 9.938 0.848 4 7 Fatty acid biosynthesis
KEGG KEGG:00500 0.00978 7.445 0.970 4 8 Starch and sucrose metabolism
KEGG KEGG:03050 0.01125 3.185 3.273 8 27 Proteasome
KEGG KEGG:00260 0.01394 4.670 1.576 5 13 Glycine, serine and threonine metabolism
KEGG KEGG:00565 0.01449 11.105 0.606 3 5 Ether lipid metabolism
KEGG KEGG:03060 0.01598 5.950 1.091 4 9 Protein export
KEGG KEGG:00520 0.02014 3.458 2.303 6 19 Amino sugar and nucleotide sugar metabolism
KEGG KEGG:00062 0.02643 7.395 0.727 3 6 Fatty acid elongation
KEGG KEGG:00280 0.03283 2.990 2.545 6 21 Valine, leucine and isoleucine degradation
KEGG KEGG:00510 0.03447 4.241 1.333 4 11 N-Glycan biosynthesis
GO: Biological process GO:0043436 0.00000 6.352 6.248 23 63 oxoacid metabolic process
GO: Biological process GO:0044283 0.00000 8.797 2.538 12 26 small molecule biosynthetic process
GO: Biological process GO:1901607 0.00080 11.851 0.893 5 9 alpha-amino acid biosynthetic process
GO: Biological process GO:0006544 0.00095 Inf 0.298 3 3 glycine metabolic process
GO: Biological process GO:0046394 0.00122 9.919 0.953 5 10 carboxylic acid biosynthetic process
GO: Biological process GO:0055086 0.00134 3.024 5.951 14 60 nucleobase-containing small molecule metabolic process
GO: Biological process GO:0044723 0.00144 5.593 1.884 7 19 single-organism carbohydrate metabolic process
GO: Biological process GO:0006633 0.00147 9.471 0.992 5 10 fatty acid biosynthetic process
GO: Biological process GO:0032787 0.00225 8.094 1.067 5 11 monocarboxylic acid metabolic process
GO: Biological process GO:0044281 0.00245 3.062 4.970 12 60 small molecule metabolic process
GO: Biological process GO:0072524 0.00393 6.751 1.190 5 12 pyridine-containing compound metabolic process
GO: Biological process GO:0046496 0.00393 6.751 1.190 5 12 nicotinamide nucleotide metabolic process
GO: Biological process GO:0019637 0.00690 2.348 7.736 15 78 organophosphate metabolic process
GO: Biological process GO:0009069 0.00762 14.388 0.484 3 5 serine family amino acid metabolic process
GO: Biological process GO:0006098 0.00819 13.981 0.496 3 5 pentose-phosphate shunt
GO: Biological process GO:0006081 0.00819 13.981 0.496 3 5 cellular aldehyde metabolic process
GO: Biological process GO:0006487 0.00976 Inf 0.198 2 2 protein N-linked glycosylation
GO: Biological process GO:0006890 0.00976 Inf 0.198 2 2 retrograde vesicle-mediated transport, Golgi to ER
GO: Biological process GO:0034637 0.00976 Inf 0.198 2 2 cellular carbohydrate biosynthetic process
GO: Biological process GO:0006564 0.00976 Inf 0.198 2 2 L-serine biosynthetic process
GO: Biological process GO:0009186 0.00976 Inf 0.198 2 2 deoxyribonucleoside diphosphate metabolic process
GO: Biological process GO:0072350 0.00976 Inf 0.198 2 2 tricarboxylic acid metabolic process
GO: Biological process GO:0009117 0.01001 2.598 5.157 11 52 nucleotide metabolic process
GO: Biological process GO:0006732 0.01019 4.894 1.440 5 15 coenzyme metabolic process
GO: Biological process GO:1901576 0.01144 1.661 31.143 42 319 organic substance biosynthetic process
GO: Biological process GO:0043413 0.01201 6.248 0.992 4 10 macromolecule glycosylation
GO: Biological process GO:0006796 0.01390 2.130 8.331 15 84 phosphate-containing compound metabolic process
GO: Biological process GO:0008652 0.01451 9.490 0.585 3 6 cellular amino acid biosynthetic process
GO: Biological process GO:0006090 0.01520 9.311 0.595 3 6 pyruvate metabolic process
GO: Biological process GO:0006733 0.01568 4.279 1.587 5 16 oxidoreduction coenzyme metabolic process
GO: Biological process GO:0044255 0.01737 2.825 3.471 8 35 cellular lipid metabolic process
GO: Biological process GO:0019318 0.01746 5.350 1.091 4 11 hexose metabolic process
GO: Biological process GO:1901135 0.02290 2.030 8.034 14 81 carbohydrate derivative metabolic process
GO: Biological process GO:0009101 0.02422 4.676 1.190 4 12 glycoprotein biosynthetic process
GO: Biological process GO:0046148 0.02736 18.486 0.298 2 3 pigment biosynthetic process
GO: Biological process GO:0035384 0.02736 18.486 0.298 2 3 thioester biosynthetic process
GO: Biological process GO:0009133 0.02736 18.486 0.298 2 3 nucleoside diphosphate biosynthetic process
GO: Biological process GO:0006094 0.02736 18.486 0.298 2 3 gluconeogenesis
GO: Biological process GO:0006085 0.02736 18.486 0.298 2 3 acetyl-CoA biosynthetic process
GO: Biological process GO:0046364 0.02736 18.486 0.298 2 3 monosaccharide biosynthetic process
GO: Biological process GO:0033014 0.02736 18.486 0.298 2 3 tetrapyrrole biosynthetic process
GO: Biological process GO:0044249 0.03042 1.529 31.017 40 318 cellular biosynthetic process
GO: Biological process GO:0006629 0.03266 5.865 0.759 3 8 lipid metabolic process
GO: Biological process GO:0044710 0.03957 3.663 1.345 4 19 single-organism metabolic process
GO: Biological process GO:0006520 0.03989 2.741 2.623 6 28 cellular amino acid metabolic process
GO: Biological process GO:0044711 0.04270 2.163 4.794 9 54 single-organism biosynthetic process
GO: Molecular function GO:0008483 0.00006 44.799 0.618 5 6 transaminase activity
GO: Molecular function GO:0016491 0.00091 2.166 15.543 28 151 oxidoreductase activity
GO: Molecular function GO:0030170 0.00248 5.977 1.544 6 15 pyridoxal phosphate binding
GO: Molecular function GO:0016620 0.00545 8.891 0.823 4 8 oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor
GO: Molecular function GO:0003824 0.00684 1.553 75.120 90 790 catalytic activity
GO: Molecular function GO:0016616 0.00946 4.127 1.956 6 19 oxidoreductase activity, acting on the CH-OH group of donors, NAD or NADP as acceptor
GO: Molecular function GO:0016885 0.01054 Inf 0.206 2 2 ligase activity, forming carbon-carbon bonds
GO: Molecular function GO:0004576 0.01054 Inf 0.206 2 2 oligosaccharyl transferase activity
GO: Molecular function GO:0004185 0.01054 Inf 0.206 2 2 serine-type carboxypeptidase activity
GO: Molecular function GO:0016717 0.01054 Inf 0.206 2 2 oxidoreductase activity, acting on paired donors, with oxidation of a pair of donors resulting in the reduction of molecular oxygen to two molecules of water
GO: Molecular function GO:0052689 0.02773 4.434 1.235 4 12 carboxylic ester hydrolase activity
GO: Molecular function GO:0004075 0.02948 17.616 0.309 2 3 biotin carboxylase activity
GO: Molecular function GO:0005201 0.02948 17.616 0.309 2 3 extracellular matrix structural constituent
GO: Molecular function GO:0046912 0.02948 17.616 0.309 2 3 transferase activity, transferring acyl groups, acyl groups converted into alkyl on transfer
GO: Cellular component GO:0005783 0.00032 8.058 1.529 7 15 endoplasmic reticulum
GO: Cellular component GO:1905368 0.00152 6.856 1.427 6 14 peptidase complex
GO: Cellular component GO:0000502 0.00450 6.486 1.223 5 12 proteasome complex
GO: Cellular component GO:0005789 0.00868 7.223 0.918 4 9 endoplasmic reticulum membrane
GO: Cellular component GO:0005581 0.01033 Inf 0.204 2 2 collagen trimer
GO: Cellular component GO:0016021 0.01139 1.524 63.720 77 625 integral component of membrane

Enriched KEGG and GO terms in module 5

Table S29: Results of KEGG and GO enrichment analysis for the genes in Module 5. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(5), gene.universe.modules)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04120 0.00103 4.757 2.204 8 48 Ubiquitin mediated proteolysis
KEGG KEGG:04142 0.00857 4.699 1.331 5 29 Lysosome
KEGG KEGG:04144 0.01149 3.289 2.571 7 56 Endocytosis
KEGG KEGG:00250 0.04847 7.174 0.367 2 8 Alanine, aspartate and glutamate metabolism
GO: Biological process GO:0071702 0.00018 4.080 4.366 13 94 organic substance transport
GO: Biological process GO:0045184 0.00038 3.945 4.069 12 86 establishment of protein localization
GO: Biological process GO:0006886 0.00061 4.660 2.555 9 54 intracellular protein transport
GO: Biological process GO:0070727 0.00119 4.173 2.792 9 59 cellular macromolecule localization
GO: Biological process GO:0031333 0.00220 Inf 0.095 2 2 negative regulation of protein complex assembly
GO: Biological process GO:0030835 0.00220 Inf 0.095 2 2 negative regulation of actin filament depolymerization
GO: Biological process GO:0030837 0.00220 Inf 0.095 2 2 negative regulation of actin filament polymerization
GO: Biological process GO:0051016 0.00220 Inf 0.095 2 2 barbed-end actin filament capping
GO: Biological process GO:0043242 0.00220 Inf 0.095 2 2 negative regulation of protein complex disassembly
GO: Biological process GO:0051649 0.00243 3.704 3.076 9 65 establishment of localization in cell
GO: Biological process GO:0065008 0.00546 4.422 1.703 6 36 regulation of biological quality
GO: Biological process GO:0043624 0.00639 41.840 0.142 2 3 cellular protein complex disassembly
GO: Biological process GO:1901879 0.00639 41.840 0.142 2 3 regulation of protein depolymerization
GO: Biological process GO:0032984 0.00639 41.840 0.142 2 3 macromolecular complex disassembly
GO: Biological process GO:0010639 0.00639 41.840 0.142 2 3 negative regulation of organelle organization
GO: Biological process GO:0007015 0.00686 10.622 0.426 3 9 actin filament organization
GO: Biological process GO:0032535 0.00686 10.622 0.426 3 9 regulation of cellular component size
GO: Biological process GO:0032956 0.00686 10.622 0.426 3 9 regulation of actin cytoskeleton organization
GO: Biological process GO:0008064 0.00686 10.622 0.426 3 9 regulation of actin polymerization or depolymerization
GO: Biological process GO:0046033 0.01240 20.900 0.189 2 4 AMP metabolic process
GO: Biological process GO:0044087 0.01260 7.952 0.520 3 11 regulation of cellular component biogenesis
GO: Biological process GO:0032271 0.01260 7.952 0.520 3 11 regulation of protein polymerization
GO: Biological process GO:0043623 0.02042 6.349 0.615 3 13 cellular protein complex assembly
GO: Biological process GO:0030029 0.02042 6.349 0.615 3 13 actin filament-based process
GO: Biological process GO:0033036 0.02133 3.617 1.654 5 40 macromolecule localization
GO: Biological process GO:0009168 0.02514 5.766 0.662 3 14 purine ribonucleoside monophosphate biosynthetic process
GO: Biological process GO:0051128 0.03039 5.281 0.710 3 15 regulation of cellular component organization
GO: Biological process GO:0045454 0.03039 5.281 0.710 3 15 cell redox homeostasis
GO: Biological process GO:0046129 0.03617 4.870 0.757 3 16 purine ribonucleoside biosynthetic process
GO: Biological process GO:0007010 0.03617 4.870 0.757 3 16 cytoskeleton organization
GO: Biological process GO:0048523 0.04248 4.517 0.804 3 17 negative regulation of cellular process
GO: Biological process GO:0009152 0.04248 4.517 0.804 3 17 purine ribonucleotide biosynthetic process
GO: Biological process GO:0051125 0.04732 Inf 0.047 1 1 regulation of actin nucleation
GO: Biological process GO:0015850 0.04732 Inf 0.047 1 1 organic hydroxy compound transport
GO: Biological process GO:0009607 0.04732 Inf 0.047 1 1 response to biotic stimulus
GO: Biological process GO:0030245 0.04732 Inf 0.047 1 1 cellulose catabolic process
GO: Biological process GO:0051273 0.04732 Inf 0.047 1 1 beta-glucan metabolic process
GO: Biological process GO:0051707 0.04732 Inf 0.047 1 1 response to other organism
GO: Biological process GO:0044247 0.04732 Inf 0.047 1 1 cellular polysaccharide catabolic process
GO: Biological process GO:0042742 0.04732 Inf 0.047 1 1 defense response to bacterium
GO: Biological process GO:0006892 0.04732 Inf 0.047 1 1 post-Golgi vesicle-mediated transport
GO: Biological process GO:0006895 0.04732 Inf 0.047 1 1 Golgi to endosome transport
GO: Biological process GO:0009251 0.04732 Inf 0.047 1 1 glucan catabolic process
GO: Biological process GO:0007188 0.04732 Inf 0.047 1 1 adenylate cyclase-modulating G-protein coupled receptor signaling pathway
GO: Biological process GO:0032456 0.04732 Inf 0.047 1 1 endocytic recycling
GO: Biological process GO:2000601 0.04732 Inf 0.047 1 1 positive regulation of Arp2/3 complex-mediated actin nucleation
GO: Biological process GO:0030301 0.04732 Inf 0.047 1 1 cholesterol transport
GO: Biological process GO:0071586 0.04732 Inf 0.047 1 1 CAAX-box protein processing
GO: Biological process GO:0070271 0.04931 4.212 0.852 3 18 protein complex biogenesis
GO: Biological process GO:0071822 0.04931 4.212 0.852 3 18 protein complex subunit organization
GO: Molecular function GO:0016787 0.00182 2.171 15.852 27 358 hydrolase activity
GO: Molecular function GO:0042578 0.00628 4.172 1.727 6 39 phosphoric ester hydrolase activity
GO: Molecular function GO:0004721 0.01923 4.499 1.063 4 24 phosphoprotein phosphatase activity
GO: Molecular function GO:0003993 0.02586 11.053 0.266 2 6 acid phosphatase activity
GO: Molecular function GO:0015103 0.02586 11.053 0.266 2 6 inorganic anion transmembrane transporter activity
GO: Molecular function GO:0004222 0.02586 5.574 0.664 3 15 metalloendopeptidase activity
GO: Molecular function GO:0030170 0.02586 5.574 0.664 3 15 pyridoxal phosphate binding
GO: Molecular function GO:0016831 0.03517 8.837 0.310 2 7 carboxy-lyase activity
GO: Molecular function GO:0004018 0.04428 Inf 0.044 1 1 N6-(1,2-dicarboxyethyl)AMP AMP-lyase (fumarate-forming) activity
GO: Molecular function GO:0052855 0.04428 Inf 0.044 1 1 ADP-dependent NAD(P)H-hydrate dehydratase activity
GO: Molecular function GO:0016840 0.04428 Inf 0.044 1 1 carbon-nitrogen lyase activity
GO: Molecular function GO:0008796 0.04428 Inf 0.044 1 1 bis(5’-nucleosyl)-tetraphosphatase activity
GO: Molecular function GO:0051861 0.04428 Inf 0.044 1 1 glycolipid binding
GO: Molecular function GO:0017089 0.04428 Inf 0.044 1 1 glycolipid transporter activity
GO: Molecular function GO:0003922 0.04428 Inf 0.044 1 1 GMP synthase (glutamine-hydrolyzing) activity
GO: Molecular function GO:0008810 0.04428 Inf 0.044 1 1 cellulase activity
GO: Molecular function GO:0004532 0.04428 Inf 0.044 1 1 exoribonuclease activity
GO: Molecular function GO:0004534 0.04428 Inf 0.044 1 1 5’-3’ exoribonuclease activity
GO: Molecular function GO:0070626 0.04428 Inf 0.044 1 1 (S)-2-(5-amino-1-(5-phospho-D-ribosyl)imidazole-4-carboxamido)succinate AMP-lyase (fumarate-forming) activity
GO: Molecular function GO:0004408 0.04428 Inf 0.044 1 1 holocytochrome-c synthase activity
GO: Molecular function GO:0016796 0.04428 Inf 0.044 1 1 exonuclease activity, active with either ribo- or deoxyribonucleic acids and producing 5’-phosphomonoesters
GO: Molecular function GO:0070273 0.04428 Inf 0.044 1 1 phosphatidylinositol-4-phosphate binding
GO: Cellular component GO:0005802 0.00290 Inf 0.108 2 2 trans-Golgi network
GO: Cellular component GO:0008290 0.00290 Inf 0.108 2 2 F-actin capping protein complex
GO: Cellular component GO:0031984 0.02609 11.918 0.271 2 5 organelle subcompartment

Enriched KEGG and GO terms in module 6

Table S30: Results of KEGG and GO enrichment analysis for the genes in Module 6. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(6), gene.universe.modules,)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04140 0.00898 4.614 1.343 5 43 Regulation of autophagy
KEGG KEGG:03410 0.02970 9.357 0.281 2 9 Base excision repair
GO: Biological process GO:0007264 0.00057 4.722 2.539 9 62 small GTPase mediated signal transduction
GO: Biological process GO:0006913 0.00241 9.251 0.614 4 15 nucleocytoplasmic transport
GO: Biological process GO:0050789 0.00241 2.559 11.096 20 271 regulation of biological process
GO: Biological process GO:0000394 0.00479 48.977 0.123 2 3 RNA splicing, via endonucleolytic cleavage and ligation
GO: Biological process GO:0007165 0.00485 2.719 6.142 13 150 signal transduction
GO: Biological process GO:0023052 0.00614 2.631 6.306 13 154 signaling
GO: Biological process GO:0050896 0.00745 2.428 7.985 15 195 response to stimulus
GO: Biological process GO:0008033 0.03403 4.948 0.737 3 18 tRNA processing
GO: Biological process GO:0006420 0.04095 Inf 0.041 1 1 arginyl-tRNA aminoacylation
GO: Biological process GO:0000379 0.04095 Inf 0.041 1 1 tRNA-type intron splice site recognition and cleavage
GO: Biological process GO:0043086 0.04095 Inf 0.041 1 1 negative regulation of catalytic activity
GO: Biological process GO:0010923 0.04095 Inf 0.041 1 1 negative regulation of phosphatase activity
GO: Biological process GO:0045936 0.04095 Inf 0.041 1 1 negative regulation of phosphate metabolic process
GO: Biological process GO:0016559 0.04095 Inf 0.041 1 1 peroxisome fission
GO: Biological process GO:0048034 0.04095 Inf 0.041 1 1 heme O biosynthetic process
GO: Biological process GO:0000012 0.04095 Inf 0.041 1 1 single strand break repair
GO: Biological process GO:0051336 0.04095 Inf 0.041 1 1 regulation of hydrolase activity
GO: Biological process GO:0006384 0.04095 Inf 0.041 1 1 transcription initiation from RNA polymerase III promoter
GO: Biological process GO:0015031 0.04682 2.370 3.399 7 83 protein transport
GO: Molecular function GO:0019001 0.00049 4.645 2.429 9 66 guanyl nucleotide binding
GO: Molecular function GO:0005525 0.00049 4.645 2.429 9 66 GTP binding
GO: Molecular function GO:0003924 0.00084 6.561 1.178 6 32 GTPase activity
GO: Molecular function GO:0000213 0.00133 Inf 0.074 2 2 tRNA-intron endonuclease activity
GO: Molecular function GO:0016894 0.00391 54.000 0.110 2 3 endonuclease activity, active with either ribo- or deoxyribonucleic acids and producing 3’-phosphomonoesters
GO: Molecular function GO:0004521 0.01241 17.978 0.184 2 5 endoribonuclease activity
GO: Molecular function GO:0004518 0.01890 6.288 0.589 3 16 nuclease activity
GO: Molecular function GO:0004814 0.03680 Inf 0.037 1 1 arginine-tRNA ligase activity
GO: Molecular function GO:0008495 0.03680 Inf 0.037 1 1 protoheme IX farnesyltransferase activity
GO: Molecular function GO:0001106 0.03680 Inf 0.037 1 1 RNA polymerase II transcription corepressor activity
GO: Molecular function GO:0005488 0.04284 1.655 37.944 45 1031 binding
GO: Molecular function GO:0004842 0.04980 4.070 0.846 3 23 ubiquitin-protein transferase activity
GO: Cellular component GO:0044798 0.03728 8.314 0.318 2 8 nuclear transcription factor complex
GO: Cellular component GO:0000214 0.03977 Inf 0.040 1 1 tRNA-intron endonuclease complex
GO: Cellular component GO:0000126 0.03977 Inf 0.040 1 1 transcription factor TFIIIB complex

Enriched KEGG and GO terms in module 7

Table S31: Results of KEGG and GO enrichment analysis for the genes in Module 7. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(7), gene.universe.modules)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:04320 0.00313 14.022 0.321 3 10 Dorso-ventral axis formation
KEGG KEGG:04068 0.00434 7.427 0.707 4 22 FoxO signaling pathway
KEGG KEGG:00511 0.01389 15.909 0.193 2 6 Other glycan degradation
KEGG KEGG:04070 0.02071 6.082 0.611 3 19 Phosphatidylinositol signaling system
KEGG KEGG:00562 0.02720 5.396 0.675 3 21 Inositol phosphate metabolism
GO: Biological process GO:0007017 0.02023 6.159 0.606 3 18 microtubule-based process
GO: Biological process GO:0007165 0.02140 2.439 5.050 10 150 signal transduction
GO: Biological process GO:0022610 0.02348 5.768 0.640 3 19 biological adhesion
GO: Biological process GO:0023052 0.02543 2.361 5.185 10 154 signaling
GO: Biological process GO:0007156 0.02719 10.057 0.269 2 8 homophilic cell adhesion via plasma membrane adhesion molecules
GO: Biological process GO:0098609 0.02719 10.057 0.269 2 8 cell-cell adhesion
GO: Biological process GO:0034214 0.03367 Inf 0.034 1 1 protein hexamerization
GO: Biological process GO:0031117 0.03367 Inf 0.034 1 1 positive regulation of microtubule depolymerization
GO: Biological process GO:0043243 0.03367 Inf 0.034 1 1 positive regulation of protein complex disassembly
GO: Molecular function GO:0016887 0.00665 4.109 1.745 6 41 ATPase activity
GO: Molecular function GO:0016773 0.01212 2.708 3.830 9 90 phosphotransferase activity, alcohol group as acceptor
GO: Molecular function GO:0008270 0.01483 2.201 6.809 13 160 zinc ion binding
GO: Molecular function GO:0004553 0.02328 5.820 0.638 3 15 hydrolase activity, hydrolyzing O-glycosyl compounds
GO: Molecular function GO:0016301 0.02751 2.314 4.383 9 103 kinase activity
GO: Molecular function GO:0046872 0.03143 1.680 16.766 24 394 metal ion binding
GO: Molecular function GO:0045131 0.04255 Inf 0.043 1 1 pre-mRNA branch point binding
GO: Molecular function GO:0004565 0.04255 Inf 0.043 1 1 beta-galactosidase activity
GO: Molecular function GO:0008568 0.04255 Inf 0.043 1 1 microtubule-severing ATPase activity
GO: Cellular component GO:0090544 0.04772 Inf 0.048 1 1 BAF-type complex
GO: Cellular component GO:0030992 0.04772 Inf 0.048 1 1 intraciliary transport particle B

Enriched KEGG and GO terms in module 8

Table S32: Results of KEGG and GO enrichment analysis for the genes in Module 8. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(8), gene.universe.modules)
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:00190 0.000 390.754 1.305 26 49 Oxidative phosphorylation
KEGG KEGG:01100 0.000 66.522 9.107 28 342 Metabolic pathways
GO: Biological process GO:0009126 0.00000 87.347 0.300 8 22 purine nucleoside monophosphate metabolic process
GO: Biological process GO:0046034 0.00000 117.688 0.205 7 15 ATP metabolic process
GO: Biological process GO:0006163 0.00000 67.683 0.355 8 26 purine nucleotide metabolic process
GO: Biological process GO:0042278 0.00000 67.683 0.355 8 26 purine nucleoside metabolic process
GO: Biological process GO:0009161 0.00000 67.683 0.355 8 26 ribonucleoside monophosphate metabolic process
GO: Biological process GO:0009144 0.00000 85.352 0.246 7 18 purine nucleoside triphosphate metabolic process
GO: Biological process GO:0009259 0.00000 55.169 0.409 8 30 ribonucleotide metabolic process
GO: Biological process GO:0009119 0.00000 50.476 0.437 8 32 ribonucleoside metabolic process
GO: Biological process GO:0009199 0.00000 72.087 0.273 7 20 ribonucleoside triphosphate metabolic process
GO: Biological process GO:0015986 0.00000 541.500 0.082 5 6 ATP synthesis coupled proton transport
GO: Biological process GO:1901657 0.00000 48.411 0.450 8 33 glycosyl compound metabolic process
GO: Biological process GO:0009168 0.00000 89.667 0.191 6 14 purine ribonucleoside monophosphate biosynthetic process
GO: Biological process GO:0009206 0.00000 180.167 0.109 5 8 purine ribonucleoside triphosphate biosynthetic process
GO: Biological process GO:0046129 0.00000 71.600 0.218 6 16 purine ribonucleoside biosynthetic process
GO: Biological process GO:0009152 0.00000 65.030 0.232 6 17 purine ribonucleotide biosynthetic process
GO: Biological process GO:0009124 0.00000 54.923 0.259 6 19 nucleoside monophosphate biosynthetic process
GO: Biological process GO:0009142 0.00000 107.900 0.136 5 10 nucleoside triphosphate biosynthetic process
GO: Biological process GO:0072522 0.00000 50.952 0.273 6 20 purine-containing compound biosynthetic process
GO: Biological process GO:0006753 0.00000 26.387 0.723 8 53 nucleoside phosphate metabolic process
GO: Biological process GO:0009163 0.00000 44.500 0.300 6 22 nucleoside biosynthetic process
GO: Biological process GO:0046390 0.00000 44.500 0.300 6 22 ribose phosphate biosynthetic process
GO: Biological process GO:1902600 0.00000 76.929 0.164 5 12 hydrogen ion transmembrane transport
GO: Biological process GO:0098660 0.00000 76.929 0.164 5 12 inorganic ion transmembrane transport
GO: Biological process GO:0098655 0.00000 76.929 0.164 5 12 cation transmembrane transport
GO: Biological process GO:0006818 0.00000 67.250 0.177 5 13 hydrogen transport
GO: Biological process GO:0015672 0.00000 48.773 0.218 5 16 monovalent inorganic cation transport
GO: Biological process GO:0009165 0.00000 25.143 0.464 6 34 nucleotide biosynthetic process
GO: Biological process GO:0006793 0.00000 14.946 1.160 8 85 phosphorus metabolic process
GO: Biological process GO:0055085 0.00001 18.865 0.587 6 43 transmembrane transport
GO: Biological process GO:0044281 0.00002 10.456 1.979 9 145 small molecule metabolic process
GO: Biological process GO:0006811 0.00003 21.180 0.409 5 30 ion transport
GO: Biological process GO:0015980 0.00004 32.485 0.218 4 16 energy derivation by oxidation of organic compounds
GO: Biological process GO:1902578 0.00020 13.050 0.614 5 45 single-organism localization
GO: Biological process GO:0044711 0.00045 8.719 1.133 6 83 single-organism biosynthetic process
GO: Biological process GO:0042773 0.00052 166.615 0.041 2 3 ATP synthesis coupled electron transport
GO: Biological process GO:1901564 0.00138 5.740 2.566 8 188 organonitrogen compound metabolic process
GO: Biological process GO:0015991 0.00465 27.641 0.109 2 8 ATP hydrolysis coupled proton transport
GO: Biological process GO:0022904 0.01186 Inf 0.012 1 1 respiratory electron transport chain
GO: Biological process GO:0016310 0.01244 15.007 0.177 2 13 phosphorylation
GO: Biological process GO:0034244 0.01365 Inf 0.014 1 1 negative regulation of transcription elongation from RNA polymerase II promoter
GO: Biological process GO:0032784 0.01365 Inf 0.014 1 1 regulation of DNA-templated transcription, elongation
GO: Biological process GO:0006122 0.01365 Inf 0.014 1 1 mitochondrial electron transport, ubiquinol to cytochrome c
GO: Biological process GO:0051234 0.01424 3.752 2.894 7 212 establishment of localization
GO: Biological process GO:0006139 0.02489 3.325 4.058 8 318 nucleobase-containing compound metabolic process
GO: Biological process GO:0008152 0.02575 4.424 8.981 13 658 metabolic process
GO: Biological process GO:1902679 0.02712 77.357 0.027 1 2 negative regulation of RNA biosynthetic process
GO: Biological process GO:0044208 0.02712 77.357 0.027 1 2 ‘de novo’ AMP biosynthetic process
GO: Biological process GO:0045934 0.02712 77.357 0.027 1 2 negative regulation of nucleobase-containing compound metabolic process
GO: Biological process GO:0009890 0.02712 77.357 0.027 1 2 negative regulation of biosynthetic process
GO: Biological process GO:0045892 0.02712 77.357 0.027 1 2 negative regulation of transcription, DNA-templated
GO: Biological process GO:0010605 0.02712 77.357 0.027 1 2 negative regulation of macromolecule metabolic process
GO: Biological process GO:0022900 0.03255 49.136 0.033 1 3 electron transport chain
GO: Biological process GO:0055114 0.03654 39.556 0.037 1 4 oxidation-reduction process
GO: Molecular function GO:0046933 0.00000 Inf 0.072 5 5 proton-transporting ATP synthase activity, rotational mechanism
GO: Molecular function GO:0015077 0.00000 44.340 0.374 8 26 monovalent inorganic cation transmembrane transporter activity
GO: Molecular function GO:0008324 0.00000 20.211 0.676 8 47 cation transmembrane transporter activity
GO: Molecular function GO:0042625 0.00000 71.167 0.158 5 11 ATPase coupled ion transmembrane transporter activity
GO: Molecular function GO:0022891 0.00000 15.243 1.006 9 70 substrate-specific transmembrane transporter activity
GO: Molecular function GO:0008137 0.00000 163.048 0.086 4 6 NADH dehydrogenase (ubiquinone) activity
GO: Molecular function GO:0016655 0.00000 163.048 0.086 4 6 oxidoreductase activity, acting on NAD(P)H, quinone or similar compound as acceptor
GO: Molecular function GO:0003954 0.00000 163.048 0.086 4 6 NADH dehydrogenase activity
GO: Molecular function GO:0015405 0.00000 42.600 0.216 5 15 P-P-bond-hydrolysis-driven transmembrane transporter activity
GO: Molecular function GO:0005215 0.00000 10.536 1.610 10 112 transporter activity
GO: Molecular function GO:0016820 0.00000 35.458 0.244 5 17 hydrolase activity, acting on acid anhydrides, catalyzing transmembrane movement of substances
GO: Molecular function GO:0043492 0.00000 35.458 0.244 5 17 ATPase activity, coupled to movement of substances
GO: Molecular function GO:0046961 0.00003 116.727 0.072 3 5 proton-transporting ATPase activity, rotational mechanism
GO: Molecular function GO:0009055 0.00007 64.088 0.093 3 7 electron carrier activity
GO: Molecular function GO:0016887 0.00021 11.653 0.589 5 41 ATPase activity
GO: Molecular function GO:0016675 0.00059 148.957 0.043 2 3 oxidoreductase activity, acting on a heme group of donors
GO: Molecular function GO:0004129 0.00059 148.957 0.043 2 3 cytochrome-c oxidase activity
GO: Molecular function GO:0051540 0.00107 19.341 0.216 3 15 metal cluster binding
GO: Molecular function GO:0003824 0.00165 4.531 13.528 21 941 catalytic activity
GO: Molecular function GO:0016651 0.00283 35.937 0.085 2 7 oxidoreductase activity, acting on NAD(P)H
GO: Molecular function GO:0051539 0.00399 29.722 0.101 2 7 4 iron, 4 sulfur cluster binding
GO: Molecular function GO:0008121 0.01438 Inf 0.014 1 1 ubiquinol-cytochrome-c reductase activity
GO: Molecular function GO:0004019 0.01438 Inf 0.014 1 1 adenylosuccinate synthase activity
GO: Molecular function GO:0032450 0.01438 Inf 0.014 1 1 maltose alpha-glucosidase activity
GO: Molecular function GO:0015926 0.01438 Inf 0.014 1 1 glucosidase activity
GO: Molecular function GO:0016679 0.01438 Inf 0.014 1 1 oxidoreductase activity, acting on diphenols and related substances as donors
GO: Molecular function GO:0004558 0.01438 Inf 0.014 1 1 alpha-1,4-glucosidase activity
GO: Molecular function GO:0010181 0.01438 Inf 0.014 1 1 FMN binding
GO: Molecular function GO:0020037 0.01625 12.333 0.201 2 14 heme binding
GO: Molecular function GO:0016462 0.02190 3.610 1.668 5 116 pyrophosphatase activity
GO: Molecular function GO:0004784 0.02855 71.375 0.029 1 2 superoxide dismutase activity
GO: Molecular function GO:0000104 0.02855 71.375 0.029 1 2 succinate dehydrogenase activity
GO: Molecular function GO:0008308 0.04254 35.667 0.043 1 3 voltage-gated anion channel activity
GO: Cellular component GO:0031975 0.00000 43.071 0.482 9 29 envelope
GO: Cellular component GO:0005740 0.00000 54.898 0.350 8 22 mitochondrial envelope
GO: Cellular component GO:0005743 0.00000 65.674 0.266 7 16 mitochondrial inner membrane
GO: Cellular component GO:0045261 0.00000 Inf 0.067 4 4 proton-transporting ATP synthase complex, catalytic core F(1)
GO: Cellular component GO:0031090 0.00000 21.446 0.682 8 41 organelle membrane
GO: Cellular component GO:0005739 0.00000 20.338 0.610 7 42 mitochondrion
GO: Cellular component GO:0098803 0.00000 Inf 0.048 3 3 respiratory chain complex
GO: Cellular component GO:0016469 0.00003 35.579 0.200 4 12 proton-transporting two-sector ATPase complex
GO: Cellular component GO:0098798 0.00008 67.850 0.100 3 6 mitochondrial protein complex
GO: Cellular component GO:0044455 0.00008 67.850 0.100 3 6 mitochondrial membrane part
GO: Cellular component GO:0070469 0.00018 Inf 0.028 2 2 respiratory chain
GO: Cellular component GO:0070069 0.00026 Inf 0.033 2 2 cytochrome complex
GO: Cellular component GO:0044446 0.00049 4.947 3.210 10 193 intracellular organelle part
GO: Cellular component GO:0005737 0.01340 2.901 4.906 10 295 cytoplasm
GO: Cellular component GO:0044425 0.01400 3.663 8.055 13 651 membrane part
GO: Cellular component GO:0005750 0.01663 Inf 0.017 1 1 mitochondrial respiratory chain complex III
GO: Cellular component GO:0005751 0.01663 Inf 0.017 1 1 mitochondrial respiratory chain complex IV
GO: Cellular component GO:0005747 0.01663 Inf 0.017 1 1 mitochondrial respiratory chain complex I
GO: Cellular component GO:0045281 0.01663 Inf 0.017 1 1 succinate dehydrogenase complex
GO: Cellular component GO:0030964 0.01663 Inf 0.017 1 1 NADH dehydrogenase complex
GO: Cellular component GO:0032021 0.01663 Inf 0.017 1 1 NELF complex
GO: Cellular component GO:0005758 0.03300 61.773 0.033 1 2 mitochondrial intermembrane space
GO: Cellular component GO:0032991 0.03576 2.457 4.839 9 291 macromolecular complex
GO: Cellular component GO:0005741 0.04910 30.864 0.050 1 3 mitochondrial outer membrane

Enriched KEGG and GO terms in module 9

Table S33: Results of KEGG and GO enrichment analysis for the genes in Module 9. The gene universe was defined as all genes for which we found an ortholog in all four species.

GO.and.KEGG.enrichment(genes.in.module(9), gene.universe.modules)
## Warning: No results met the specified criteria. Returning 0-row data.frame
Test_type ID Pvalue OddsRatio ExpCount Count Size Term
KEGG KEGG:00230 0.00825 9.885 0.455 3 55 Purine metabolism
KEGG KEGG:00430 0.01647 134.875 0.017 1 2 Taurine and hypotaurine metabolism
KEGG KEGG:00981 0.04868 26.875 0.050 1 6 Insect hormone biosynthesis
GO: Biological process GO:0006275 0.01632 136.125 0.016 1 2 regulation of DNA replication
GO: Biological process GO:0035556 0.03782 5.298 0.794 3 97 intracellular signal transduction
GO: Molecular function GO:0004383 0.00067 101.059 0.044 2 4 guanylate cyclase activity
GO: Molecular function GO:0016829 0.00581 9.891 0.382 3 35 lyase activity
GO: Molecular function GO:0020037 0.00952 16.745 0.153 2 14 heme binding
GO: Molecular function GO:0004045 0.01093 Inf 0.011 1 1 aminoacyl-tRNA hydrolase activity
GO: Molecular function GO:0004000 0.01093 Inf 0.011 1 1 adenosine deaminase activity
GO: Molecular function GO:0030337 0.01093 Inf 0.011 1 1 DNA polymerase processivity factor activity
GO: Molecular function GO:0016702 0.02174 95.500 0.022 1 2 oxidoreductase activity, acting on single donors with incorporation of molecular oxygen, incorporation of two atoms of oxygen
GO: Molecular function GO:1901363 0.03930 2.528 7.725 12 707 heterocyclic compound binding
GO: Molecular function GO:0097159 0.03930 2.528 7.725 12 707 organic cyclic compound binding
GO: Molecular function GO:0004672 0.04241 4.420 0.798 3 73 protein kinase activity
GO: Molecular function GO:0004715 0.04303 31.796 0.044 1 4 non-membrane spanning protein tyrosine kinase activity

Inspect the gene list for the pheromone-sensitive module 4

Table S34: List of all the genes in Module 4, ranked by their within-module connectivity, k. The latter four columns give the Log\(_2\) fold-change in expression in response to queen pheromone in each of the four species.

inspect.module.genes(4) %>% 
  mutate(am_fc=log2(am_fc), bt_fc=log2(bt_fc), lf_fc=log2(lf_fc), ln_fc=log2(ln_fc)) %>% 
  rename(Gene=gene, Name=name) %>% 
  kable.table()
Gene Name k am_fc bt_fc lf_fc ln_fc
GB44431 26S protease regulatory subunit 4 isoform 1 44.223556 0.2068368 -0.0420157 -0.4280960 -0.0088204
GB49337 26S proteasome non-ATPase regulatory subunit 13 42.984225 0.1764581 -0.0655698 -0.2607125 -0.5605728
GB50750 coatomer subunit delta isoform 2 42.890303 -0.0312791 -0.0288217 -0.0588197 -0.0489833
GB45720 proteasome subunit alpha type-7-1-like 41.581027 0.1530987 -0.0949419 -0.0722067 0.0630901
GB50242 26S proteasome non-ATPase regulatory subunit 4 41.384303 0.2213651 0.0631539 -0.1328648 0.5944635
GB53174 programmed cell death 6-interacting protein isoform X1 41.242520 -0.0756447 -0.0159918 -0.0466398 -0.0545396
GB47189 H(+)/Cl(-) exchange transporter 3-like isoform X2 41.034107 0.0346407 -0.0154327 -0.1018644 -0.0454175
GB50252 GTP-binding protein SAR1b-like isoform X4 40.648326 0.3208936 -0.0667845 -0.0210473 -0.2223932
102656372 tropinone reductase 2-like 39.868937 0.1120373 0.0340800 0.3238888 0.4926542
GB53812 prolyl endopeptidase-like isoformX1 39.532524 -0.0804557 -0.0489813 -0.0926730 -0.0238204
GB45567 E3 ubiquitin-protein ligase MARCH5 isoform X5 39.470727 -0.0551062 0.0346992 0.4749971 0.0134325
GB41649 E3 ubiquitin-protein ligase MARCH6 39.278828 -0.0462292 -0.0638063 -0.0682451 0.0497685
GB43819 ATPase ASNA1 homolog 39.180343 0.3773737 -0.0065874 -0.1431066 -0.0100659
GB44941 eukaryotic peptide chain release factor GTP-binding subunit ERF3A 39.104220 -0.0593707 0.0722754 -0.0148940 -0.1104174
GB53690 protein transport protein Sec31A 38.707647 -0.0073805 0.0306890 -0.1181363 -0.0320893
GB48643 STT3, subunit of the oligosaccharyltransferase complex, homolog B 37.962742 0.1934304 0.0005876 -0.1604664 -0.0954778
GB50348 bleomycin hydrolase-like isoform X2 37.858985 -0.0331317 0.0361318 -0.0548069 0.0615163
GB43706 probable trans-2-enoyl-CoA reductase, mitochondrial-like 37.473883 -0.0105284 0.0051152 -0.0134324 0.0351066
GB40775 apoptosis-inducing factor 1, mitochondrial 36.869445 0.2000561 0.1909935 0.3170325 0.0325652
411789 protein extra bases 36.857043 0.1887237 0.0207032 -0.1285144 0.1008955
GB40483 xyloside xylosyltransferase 1-like 36.852931 0.0301872 0.0061033 -0.0806551 0.0684976
GB41617 methylcrotonoyl-CoA carboxylase beta chain, mitochondrial-like isoform X2 36.788246 0.1487599 -0.1687086 -0.2389065 -0.0591055
GB50289 signal recognition particle 54 kDa protein-like 36.640755 0.0039203 -0.0010764 -0.0138630 -0.0199337
GB50274 transitional endoplasmic reticulum ATPase TER94 36.259304 0.5435617 -0.1180270 -0.3064504 -0.0779525
GB47540 putative leucine-rich repeat-containing protein DDB_G0290503 isoform X2 36.214750 0.2775390 0.0232034 -0.1293343 0.0217957
GB47573 T-complex protein 1 subunit theta-like 36.082403 0.1562527 0.0513066 -0.0207824 -0.0623897
GB52675 26S proteasome non-ATPase regulatory subunit 12 35.929513 0.2312931 0.0482900 -0.0951427 0.7829533
GB42355 asparagine–tRNA ligase, cytoplasmic-like 35.911929 0.1286098 0.1015732 -0.1220399 -0.0430047
GB42329 segmentation protein cap’n’collar-like isoform X4 35.867197 -0.2192666 -0.1006952 -0.1213930 0.6014040
GB55494 probable nucleolar GTP-binding protein 1-like isoform 1 35.759099 0.0447120 0.0957711 3.8215256 -0.1220854
GB42773 alanine–tRNA ligase, cytoplasmic-like isoform X1 35.229118 -0.0350767 0.0415367 -0.0868974 0.0119881
GB50730 97 kDa heat shock protein isoformX1 35.063680 -0.1577197 -0.0288468 -0.2107992 -0.1611854
GB48313 transmembrane 9 superfamily member 3 34.685061 0.2534914 -0.0136668 -0.0312486 -0.0353920
GB50459 WD repeat-containing protein 36-like 34.578669 -0.1479411 -0.0430390 -0.2433271 -0.1232282
GB46035 eukaryotic translation initiation factor 4 gamma 2-like isoform X4 33.921974 -0.2214407 0.0295406 -0.2425567 -0.1486897
GB54608 probable elongator complex protein 2-like 33.814252 0.0689425 0.0691345 -0.2205388 -0.1308013
GB50177 protein TRC8 homolog 33.492549 0.0945129 0.1231066 -0.1733043 0.2465639
GB45258 isocitrate dehydrogenase [NADP] cytoplasmic isoform 2 33.420505 -0.0142164 -0.0157218 -0.1189860 -0.0987758
GB47114 dolichyl-diphosphooligosaccharide–protein glycosyltransferase subunit 2-like 33.136515 0.1350366 0.1040145 -0.1152653 -0.1108689
GB44418 protein suppressor of hairy wing isoform X2 33.079975 -0.4107368 -0.1260784 -0.2722544 0.0277971
GB54573 probable 26S proteasome non-ATPase regulatory subunit 3 isoform X2 31.928635 0.0538327 -0.0037021 -0.0681125 -0.9049955
GB55440 phosphatidylinositol transfer protein alpha isoform 31.910100 0.1654650 0.0068526 -0.0463461 0.0630027
GB41762 derlin-2-like 31.704673 0.1842082 0.0872893 -0.2212623 -0.1243794
GB49939 protein FAM188A homolog 31.551690 -0.1412746 0.1136928 -0.1907462 0.0388591
GB42648 dolichyl-diphosphooligosaccharide–protein glycosyltransferase subunit 1 31.480759 0.2655380 0.1595473 -0.1227576 -0.1662744
GB44670 luciferin 4-monooxygenase-like 31.430736 -0.0515925 0.1548945 1.1032901 0.0559438
GB43131 short-chain dehydrogenase/reductase family 16C member 6-like isoform X4 31.410234 0.1007306 0.0869099 -0.1985410 -0.0829191
GB48692 translocation protein SEC63 homolog isoform 1 31.125908 0.2857900 -0.0530291 -0.1602624 0.0209032
GB49083 casein kinase II subunit beta isoform X1 30.992393 0.2782502 0.0471649 -0.1111348 0.0698090
GB41427 catalase 30.732896 0.1430821 0.0736901 -0.3977072 -0.0121187
GB46735 eukaryotic translation initiation factor 2A-like 30.705422 -0.0411662 0.0130254 -0.1447461 -0.0105182
GB47296 transmembrane protein 19-like isoform X2 30.672830 0.4289691 -0.0545500 -0.2516466 -0.1027988
GB52168 von Willebrand factor A domain-containing protein 8-like 30.577444 0.0856555 -0.0740676 0.0014012 0.0699640
GB48812 dnaJ homolog subfamily C member 3 30.546137 0.1132367 0.0402074 -0.2195332 0.0306329
102655967 ancient ubiquitous protein 1-like 30.348262 0.4711330 0.0420199 0.1648789 0.0503451
551499 FIT family protein CG10671-like 29.740675 0.3785333 -0.0602509 -0.3180826 -0.0349339
GB49955 vacuole membrane protein 1 isoform X1 29.459325 -0.0443525 -0.0065202 -0.2963167 0.1983572
GB41285 receptor-binding cancer antigen expressed on SiSo cells 29.433269 0.0238298 0.1200911 -0.1399244 -0.1309690
GB54861 LOW QUALITY PROTEIN: counting factor associated protein D-like 29.320266 0.2298241 0.1926641 -0.2944184 -0.0974716
GB47462 protein disulfide-isomerase A3 isoform 2 29.268674 0.3049034 0.0771835 -0.2557549 0.1369471
GB46646 UPF0554 protein C2orf43 homolog 28.707580 0.3354412 -0.0495704 -0.2178741 -0.1430792
GB44396 atlastin isoform X2 28.556709 -0.0591485 -0.1777902 -0.0925969 0.3200035
GB53373 leucine-rich repeat-containing protein 58-like 28.367576 0.1837683 0.0574237 -0.2601640 0.1579574
GB55484 UBX domain-containing protein 7-like 28.345099 -0.1419776 0.0862990 -0.1770521 -0.0476737
GB47134 renin receptor-like isoform X1 28.303254 0.3303687 -0.0407767 0.3718194 0.4166502
GB43912 nicalin-1 isoform X1 28.248461 0.6287100 0.0881076 -0.3253488 -0.0103644
GB46120 aspartate aminotransferase, mitochondrial isoform 1 28.225409 0.2491141 0.0236496 0.1306639 0.0254197
GB49525 RNA-binding protein fusilli 28.209030 0.1174438 -0.0741709 -0.0349456 0.0534866
GB48597 NADH-cytochrome b5 reductase 2-like isoform X2 28.155088 0.2033803 0.0013862 -0.0996939 -0.0202651
GB44205 proteasome subunit beta type-5-like 28.006936 0.4837999 -0.0915736 -0.4335090 -0.0596112
GB52434 probable ribosome production factor 1-like 27.874103 0.0054318 0.0148853 -0.2060277 0.0182433
GB40779 transaldolase 27.760521 -0.0039251 0.0160977 -0.0440904 0.0344095
GB45582 facilitated trehalose transporter Tret1-like isoform 3 27.374644 -0.0504268 -0.1335269 0.0539026 -0.0069750
GB45698 SAGA-associated factor 11 homolog 27.343826 -0.2647791 0.0924924 -0.1384764 0.1879171
GB40265 transcriptional activator protein Pur-beta-B-like isoform X4 27.334314 0.1264999 -0.0386187 -0.1285937 -0.0782933
GB47392 protein BCCIP homolog 27.258892 0.2577727 0.1104351 0.7443079 0.1332378
GB55987 ras-related protein Rab-18-B 27.110725 0.0323400 -0.0536913 -0.0349277 -0.0504278
GB55977 eukaryotic translation initiation factor 4E-1A 27.089946 0.1705188 0.0538447 -0.0949449 0.1031615
GB45251 ubiA prenyltransferase domain-containing protein 1 homolog 26.995162 0.2292889 0.0114163 -0.1159756 0.0793336
GB48008 peroxisomal membrane protein PEX14-like 26.969623 0.0001390 0.0224702 -0.2071820 -0.0800297
GB46977 ribosome biogenesis methyltransferase WBSCR22-like 26.952365 0.0481658 0.0896746 -0.2062109 0.0893196
GB54363 ATPase family AAA domain-containing protein 3 isoform X1 26.942276 0.3943176 0.1631272 -0.1500874 -0.0561398
GB53955 FGFR1 oncogene partner 2 homolog 26.809933 0.0846268 -0.0312388 -0.1442031 0.0964404
GB51282 thioredoxin domain-containing protein 5-like isoform 1 26.691792 0.2485396 0.0763851 0.1463655 -0.0113567
GB46031 vacuolar H+ ATP synthase 16 kDa proteolipid subunit 26.645728 -0.0479109 -0.0170686 -0.2826372 0.0222715
GB54848 tumor suppressor candidate 3-like 26.523213 0.4846324 -0.0104631 -0.6272344 -0.0006124
GB49119 deoxynucleotidyltransferase terminal-interacting protein 2-like 26.458317 0.2109767 -0.0144902 -0.1065953 0.0599639
GB53080 alpha-2-macroglobulin receptor-associated protein-like 26.455789 0.0064170 -0.0306365 -0.0869340 0.0369668
GB49117 heat shock protein cognate 3 precursor 26.360858 0.2270221 -0.0395375 -0.2932567 -0.1580736
GB49240 aldehyde dehydrogenase, mitochondrial isoform 1 26.349079 0.1549590 0.1010275 -0.0376052 -0.0094109
GB55610 MOSC domain-containing protein 2, mitochondrial-like 26.339169 -0.0627471 0.0072092 0.3240534 -0.1399329
GB49307 DNA-directed RNA polymerases I and III subunit RPAC1-like isoform X1 26.293649 -0.0115285 0.0668726 0.3393313 -0.0367022
GB52729 aspartate–tRNA ligase, cytoplasmic 26.270157 0.1271826 -0.0104019 7.4806151 -0.0363266
GB40207 serine–tRNA ligase, mitochondrial 26.269427 0.0012962 -0.0721504 0.0021323 -0.0446679
GB46979 derlin-1-like 26.162259 0.6809454 -0.0344909 0.5101016 -0.0139263
GB42236 patched domain-containing protein 3-like isoform X4 25.938301 -0.2888681 0.0901237 -0.1149775 0.1142936
102653839 histone-lysine N-methyltransferase SETMAR-like 25.496262 0.2063172 -0.0636157 -0.2265030 -0.1742015
GB49180 cysteine-rich secretory protein 1-like, transcript variant X5 25.371025 -0.2540170 -0.0393153 -0.1190649 -0.2517126
GB55537 transketolase isoform 1 25.321298 1.0357857 0.0369899 -0.2479617 -0.3417730
GB54999 NAD kinase 2, mitochondrial-like 25.209366 0.4540230 -0.2140000 -0.0815604 -0.0922070
GB54101 HEAT repeat-containing protein 3-like 24.883603 -0.2253708 -0.0872323 -0.1050610 0.0597797
GB55490 uncharacterized protein LOC410793 24.753469 -0.0477751 -0.0681408 -0.4730765 0.2615252
GB46579 glucose-6-phosphate 1-dehydrogenase isoform X3 24.688398 0.6482683 -0.1000294 -0.3650464 -0.1593256
GB50096 pantothenate kinase 1-like isoform X2 24.586554 0.8477323 -0.0870535 -0.3693640 -0.0267439
GB54112 adenine phosphoribosyltransferase isoform X1 24.536162 0.2345084 0.0448087 1.4763523 0.1039490
GB47432 5-aminolevulinate synthase, erythroid-specific, mitochondrial-like 24.361288 0.3065397 -0.2485980 -0.3612845 -0.0388571
GB40783 glucose-6-phosphate isomerase-like 24.207603 -0.2439304 -0.1024763 -0.0910389 -0.0013179
GB54298 stromal cell-derived factor 2-like protein 1-like isoformX2 24.138324 0.3180715 0.0516537 -0.2166825 1.5192543
GB44457 FGGY carbohydrate kinase domain-containing protein-like isoform X2 23.955079 0.3022943 -0.1605569 -0.2354506 -0.0710812
GB48408 protein catecholamines up 23.947718 0.0141547 -0.0116125 -0.1088589 0.0730103
GB48847 DNA replication licensing factor Mcm3 23.786913 -0.3084852 0.2500155 -0.2998054 0.1204342
GB46657 galactokinase-like 23.579329 0.1002480 0.0684625 -0.5178679 0.0198896
GB52347 saccharopine dehydrogenase-like oxidoreductase-like isoform 1 23.401023 0.3645361 -0.4951154 0.2533578 -0.1998256
GB51782 carboxypeptidase Q-like isoform 1 23.387758 0.3346236 -0.0203412 -0.0649589 -0.1664672
GB48308 probable pyruvate dehydrogenase E1 component subunit alpha, mitochondrial-like isoform X2 23.311737 -0.2837578 -0.1078497 0.1711523 0.5184012
GB44557 probable ribonuclease ZC3H12C-like isoformX1 23.279307 0.0744929 -0.0447778 -0.1440084 -0.3265611
GB47941 cyclic AMP response element-binding protein A-like 23.225979 -0.3397125 0.1288849 -0.1450569 -0.3071147
GB42732 long-chain-fatty-acid–CoA ligase 3-like isoform X2 23.218782 0.4989058 -0.0146724 -0.3252347 -0.1571386
GB52724 protein 5NUC-like isoform X2 23.028043 0.0972367 0.0206395 -0.1179516 0.0023551
GB46772 very-long-chain enoyl-CoA reductase-like 23.018130 0.7467499 -0.2199431 -0.2011022 -0.4308688
GB44008 BTB/POZ domain-containing protein 17 isoform X1 22.839645 0.3154921 0.1167502 -0.1116056 -0.0483891
GB55511 growth/differentiation factor 8-like isoform 1 22.816925 0.4352292 0.1588802 -0.4870545 0.0743345
GB54601 protein disulfide-isomerase A6-like isoform 1 22.775763 0.4324571 0.1249594 -0.1467693 -0.0779340
GB49342 sugar phosphate exchanger 2-like isoform X3 22.718190 -0.2236853 -0.0107231 -0.0067022 0.0247381
GB49348 transmembrane protein 115-like 22.714857 0.3394745 -0.0382297 -0.0306424 -0.0288120
GB41388 glycerol-3-phosphate dehydrogenase 22.668744 -0.0851797 -0.1391961 -0.1883058 0.2562985
GB49336 acetyl-CoA carboxylase-like isoform X9 22.667437 0.3952476 -0.1602047 0.1869465 -0.2268771
GB54056 serine hydroxymethyltransferase, cytosolic isoform X3 22.549057 0.4140579 0.1933755 -0.3256797 -0.2607203
GB44640 solute carrier family 52, riboflavin transporter, member 3-A-like isoform X2 22.453147 -0.1275523 -0.1027834 0.1884364 -0.2170403
GB49826 sterol O-acyltransferase 1-like 22.192329 0.0951372 0.1465247 -0.2836459 0.0229186
GB47694 globin 1 22.014317 -0.0509277 0.1091362 -0.1515248 -0.1010404
GB52074 6-phosphogluconate dehydrogenase, decarboxylating 21.966722 0.8095794 -0.1426001 -0.4446501 -0.6031632
GB48195 acyl-CoA Delta(11) desaturase-like 21.937703 0.4943072 -0.1931849 0.6995588 0.6686102
GB45213 acyl-CoA synthetase short-chain family member 3, mitochondrial-like isoform X2 21.833726 0.6513876 0.2239474 -0.5637999 -0.2397701
GB50680 mannose-P-dolichol utilization defect 1 protein homolog isoform X2 21.555807 0.4656771 -0.3933720 -0.2207091 -0.0486393
GB45775 pancreatic triacylglycerol lipase-like isoform X2 21.506443 0.3197015 0.0505266 -0.8880584 0.0691686
GB41916 uncharacterized protein LOC726658 isoform 1 21.370720 0.3361149 0.3728404 -0.0276391 -0.0165127
GB52458 cysteine-rich with EGF-like domain protein 2-like 21.264629 -0.2710389 0.0498794 -0.3606772 -0.0178730
GB40278 probable methylmalonate-semialdehyde dehydrogenase [acylating], mitochondrial isoform X4 21.241766 -0.1582318 0.0029943 0.0294265 -0.0342272
GB54216 ATP-citrate synthase isoform X2 21.223912 0.8455868 -0.2267974 -0.4457293 -0.3264580
552211 protein THEM6-like 21.184585 0.7375726 -0.1442659 0.3923799 -0.5969306
GB55533 RNA-binding protein squid-like 20.856600 0.0651253 0.0778979 -0.0906335 -0.1167986
GB48859 UPF0160 protein MYG1, mitochondrial-like isoform X2 20.818643 0.2361138 0.2491324 -0.2080104 -0.0332518
GB49433 H/ACA ribonucleoprotein complex subunit 2-like protein 20.790828 0.5517963 0.1195184 -0.1634197 0.0024375
GB42237 N6-adenosine-methyltransferase 70 kDa subunit-like 20.731214 -0.0894263 0.2756185 -0.0857468 -0.0529242
GB46921 monocarboxylate transporter 12-like 20.714713 0.1807485 0.0007541 -0.1003586 -0.2148760
GB45596 elongation of very long chain fatty acids protein 6-like 20.705352 0.5247867 -0.4973462 -0.5304114 -0.5077637
GB50013 proclotting enzyme 20.601511 0.2512238 -0.9767295 -0.5331162 -0.2907466
GB55263 putative fatty acyl-CoA reductase CG5065-like 20.420422 -0.0329414 -0.2619832 -0.8318867 -0.3621781
GB54404 elongation of very long chain fatty acids protein AAEL008004-like 20.311401 2.0337166 -0.0397052 -0.1819294 -0.1518170
GB55094 protein neuralized isoform X3 20.264296 -0.6029457 0.1077662 -0.6403894 -0.0243416
GB54427 ribonucleoside-diphosphate reductase subunit M2 isoform X2 20.130036 0.0040836 0.1604850 -0.0329101 0.0177491
GB54538 uncharacterized protein LOC411248 isoform X5 20.086236 -0.4660266 -0.2286794 -0.0025983 -0.0413626
GB52768 alkaline phosphatase, tissue-nonspecific isozyme-like isoform X1 20.080226 -0.0170971 0.1366385 -0.0403085 -0.0385024
GB51580 long-chain-fatty-acid–CoA ligase ACSBG2 isoform X1 20.069108 -0.0990216 -0.1748159 -0.2690449 -0.1224712
GB50871 serine/threonine-protein kinase SIK2-like isoform X2 19.916686 0.0606616 -0.1441363 -0.2312372 0.2129038
GB53287 sialin-like isoform X4 19.620220 -0.0297581 -0.1059771 -0.1192229 -0.2783113
GB49653 probable phosphoserine aminotransferase-like 19.478348 0.4313976 0.0935267 0.0591799 -0.0947978
GB47495 nucleotide exchange factor SIL1-like 19.344565 -0.1521038 0.1578777 -0.0097726 -0.0068981
GB51723 60S ribosomal export protein NMD3 19.222509 -0.0712135 0.1664404 0.1759210 -0.0663748
GB48628 RNA-binding protein Nova-1-like isoform X2 19.214104 0.0515613 0.0209321 -0.5161615 -0.1714978
GB50626 phospholipase D3-like isoform X7 19.160241 -0.1767844 -0.0946056 -0.1617004 -0.0368420
GB54331 cathepsin L-like isoform X2 19.064368 0.0167944 -0.0794017 -0.3784244 -0.0640108
GB53412 fatty acid synthase-like 18.867764 1.1288740 -0.3170657 0.5061635 -0.1800755
GB51753 uncharacterized protein LOC100576760 isoform X2 18.820612 0.0773965 0.1404132 -0.0662854 -0.1625608
100577899 DNA replication complex GINS protein SLD5-like 18.733489 0.3469362 0.1156921 -0.2384693 -0.0444013
GB42899 uncharacterized protein LOC551133 isoform X2 18.387282 0.1289445 0.0095466 -0.0099508 -0.0564785
GB52446 uncharacterized protein LOC726987 isoform X5 18.323554 -0.5188239 -0.2066036 -0.3780834 -0.1773838
GB52351 porphobilinogen deaminase-like 18.239714 -0.3935509 -0.0800125 -0.5113538 0.0303557
GB45381 putative sodium-coupled neutral amino acid transporter 7-like 18.232994 0.2322221 -0.2991610 -0.1452851 -0.1044424
GB41886 protein transport protein Sec61 subunit alpha isoform 2 18.215808 0.7287917 -0.0327566 -0.2604661 -0.3382911
GB52153 U3 small nucleolar RNA-associated protein 15 homolog 18.207361 0.1742820 0.1472587 -0.0709591 -0.0205023
GB48203 laminin subunit beta-1 isoform X2 18.135401 -0.0687494 0.0552598 -0.1815586 -0.5195985
GB51647 4-aminobutyrate aminotransferase, mitochondrial-like isoform X2 18.132631 0.5676800 0.0956367 -0.1094744 -0.0314973
GB52454 mitochondrial pyruvate carrier 2-like 18.031851 -0.4590473 0.0544465 -0.1848845 0.0310854
GB49942 mitochondrial dicarboxylate carrier-like isoform 1 17.737991 0.1890512 -0.0364015 -0.1444554 -0.0878453
GB51614 probable methylthioribulose-1-phosphate dehydratase-like 17.686800 -0.0358269 -0.0730244 2.4507128 0.0926130
GB41011 lateral signaling target protein 2 homolog 17.643002 -0.0761978 -0.1736913 -0.5037217 -0.0906862
GB49869 microsomal triglyceride transfer protein large subunit isoform X1 17.589998 0.1389107 0.2371633 -0.4710017 -0.8792260
GB55432 glucosidase 2 subunit beta-like 17.428805 0.4916918 0.1151030 -0.1781667 0.0426794
GB40071 uncharacterized protein LOC410446 17.398408 0.0764242 0.0301336 1.2168758 0.0847128
GB44888 MATH and LRR domain-containing protein PFE0570w-like 17.235171 0.0429701 -0.0248396 0.0078619 -0.1299584
GB54610 thiamine transporter 2-like, transcript variant X2 17.225455 -0.4767433 0.1088769 -0.1870434 -0.3209313
GB54661 phosphoglucomutase isoform X2 17.097639 -0.3363439 -0.1135590 -0.1806090 -0.2087559
GB46422 proton-coupled amino acid transporter 1 16.930428 0.2093788 -0.1884596 0.0117507 -0.1665571
GB45177 uncharacterized protein LOC725324 isoform X1 16.879588 0.4068916 -0.0574424 -0.1430491 0.3385230
GB49633 RNA 3’-terminal phosphate cyclase-like protein-like isoform X2 16.859461 0.1575109 -0.0608420 -0.0908976 0.0954425
GB40141 venom serine carboxypeptidase 16.809434 0.1223739 -0.3228364 -0.3209092 -0.0884225
GB40280 pyruvate carboxylase, mitochondrial isoform X1 16.742568 -0.6020803 -0.0510597 -0.2153246 -0.3460215
GB49757 fatty acid binding protein 16.704757 0.4148758 -0.1762910 0.3588453 -0.1569230
GB46661 sodium-independent sulfate anion transporter-like isoform X1 16.610634 -0.2846534 0.2134063 -0.0536858 -0.0012242
GB45210 translocon-associated protein subunit gamma-like 16.589367 -0.2578927 -0.0623966 -0.0363309 -0.1380282
GB47383 U4/U6 small nuclear ribonucleoprotein Prp4 16.525971 0.0183237 -0.0212914 -0.0394002 0.0668049
GB42787 dentin sialophosphoprotein-like isoform X4 16.515172 0.1684747 0.3042534 -0.2740726 -0.0993491
102655896 nucleoplasmin-like protein-like isoform X4 16.340267 0.1679860 0.1843370 -0.1048845 0.0246945
GB55474 protein pygopus 16.236962 0.2676167 0.0707588 -0.0549138 0.0726924
GB51125 inositol-3-phosphate synthase 1-B isoform X2 16.234124 -0.1324499 0.0450646 -0.1206895 -0.1431645
GB45968 collagen alpha-1(IV) chain-like isoform 1 16.142244 -0.1021189 -0.2851870 -0.1437885 -0.1852569
GB44537 myosin-IA 16.130906 -0.3302817 -0.0513892 0.0332848 -0.1087754
GB45824 phosphoserine phosphatase isoform X2 15.998310 0.1362108 -0.0741826 -0.1520385 0.9771061
GB53567 branched-chain-amino-acid aminotransferase, cytosolic-like isoform 1 15.898775 -0.1946488 -0.1506045 -0.1192245 0.0252445
724293 protein yellow 15.838484 0.1487303 -0.2653227 0.9050534 0.0119983
GB44138 l-2-hydroxyglutarate dehydrogenase, mitochondrial-like isoform X3 15.463787 -0.0605374 -0.0645523 -0.0579366 -0.0117976
GB45975 LIM/homeobox protein Lhx3 15.448320 -1.4912892 0.1699440 -0.5350890 -0.2095720
GB44420 hydroxymethylglutaryl-CoA synthase 1 isoform X2 15.447539 0.0319813 -1.4782209 -0.2339946 -0.2200166
GB43942 putative serine protease K12H4.7-like isoform X2 15.444385 0.6725080 0.0163704 -0.1396986 0.1787550
GB42629 chromatin accessibility complex protein 1-like 15.273897 0.1251692 0.1625803 -0.0870455 -0.0091544
GB42541 carbonic anhydrase-related protein 10-like isoform X3 15.217357 -0.0902229 -0.2070180 -0.4223262 -0.1162996
GB54391 putative glycogen [starch] synthase-like isoform X1 15.171482 -0.1572320 -0.1100485 -0.0326887 -0.1545854
GB52496 epoxide hydrolase 4-like isoform X4 15.110661 0.2774522 0.0115722 -0.3747157 -0.0800490
GB51598 translocon-associated protein subunit beta isoform 2 14.774053 0.5583941 0.0371216 -0.0403127 -0.1591828
GB49095 high affinity copper uptake protein 1-like isoformX1 14.620522 0.5230884 -0.1010762 -0.2729704 -0.0231513
GB54888 2-acylglycerol O-acyltransferase 1-like isoform X1 14.550168 0.6685157 0.0466928 -0.0917668 -0.1179655
GB42264 myb-like protein X-like 14.521676 -0.6252822 -0.1368822 1.0730476 -0.0070602
GB45943 collagen alpha-5(IV) chain 14.385447 -0.0141205 -0.1686619 -0.0306632 0.1661617
GB51236 acyl-CoA Delta(11) desaturase isoform X2 14.282561 0.7514364 0.0473029 -0.6010006 0.4886544
GB47503 delta-1-pyrroline-5-carboxylate synthase-like isoform X3 14.246721 -0.4533711 -0.1181787 -0.0922763 -0.0916646
GB47839 calumenin 14.227729 0.2508064 0.1073882 1.1338349 0.6543477
GB40747 GMP reductase 2-like isoform 1 14.074250 -0.1389808 -0.0848805 0.0539909 0.0060923
GB55661 neuronal membrane glycoprotein M6-a-like isoform X2 13.870018 0.2916694 0.0445663 0.0406151 0.0845796
GB49854 alpha-amylase precursor 13.835878 0.4857671 0.0835219 -1.6759631 0.9168179
726965 uncharacterized protein LOC726965 13.828477 -0.1511445 -0.1317802 0.1458579 -0.3221607
102655415 uncharacterized protein LOC102655415 13.761128 -0.1886490 -0.2064529 -0.8759375 -0.3895903
GB52114 protein trachealess-like isoform X7 13.706700 -0.6009081 -0.0822315 2.8207841 0.0081549
GB43216 uncharacterized protein LOC413583 isoform X2 13.521796 -0.2362268 -0.1658183 -0.4291904 -0.6447770
GB47449 nucleoporin NUP188 homolog 13.432553 0.0398209 0.1257927 -0.3579522 -0.0552367
GB53230 adipokinetic hormone receptor 13.346403 -0.1559642 0.0488804 -0.4935836 -0.3911266
GB42738 protein cueball-like 13.218575 0.0792556 0.0187766 -0.3277604 -0.1859564
GB42468 phospholipase B1, membrane-associated-like isoform X1 13.019295 0.1712758 -2.6550613 -0.2391406 0.1282518
GB48521 RNA polymerase II elongation factor ELL2-like isoform X1 12.917540 -0.0107311 -0.1580317 -0.1465078 0.0207912
GB49321 D-arabinitol dehydrogenase 1-like 12.778844 0.3850348 -0.0314272 -0.1281534 -0.1467144
GB53404 protein fork head-like isoform 1 12.776526 -2.0510009 0.0551431 0.4763584 -0.2108822
411557 protein FAM46A-like isoformX2 12.640439 -0.3724492 0.1541695 -0.1698355 -0.0530527
GB44850 origin recognition complex subunit 3-like 12.544410 0.2060399 -0.0628445 -0.2511858 0.1533299
GB51077 dystrotelin-like isoform X1 12.364985 -0.2613290 0.1545091 -0.4736396 0.0442161
GB49543 alanine–glyoxylate aminotransferase 2-like 12.351536 0.3435971 -0.1281697 -0.1746713 -0.5539103
GB52712 serine/arginine repetitive matrix protein 2-like isoform X1 12.310149 0.1347869 0.2130550 -0.1568323 0.1329923
GB53036 serine/threonine-protein kinase Warts-like isoform X1 12.294727 -0.1758171 0.0278491 -0.2505460 0.0098058
GB46917 uncharacterized protein LOC726071 12.249764 0.1372400 0.0917500 -0.1651023 0.1279429
GB53661 methyltransferase-like isoform X3 12.132568 -0.2274413 -0.0795270 2.0586400 -0.0170579
GB51278 innexin inx3 12.091606 0.3830713 0.0406630 0.0169686 -0.1518675
GB52161 cuticular protein 28 precursor 11.933221 0.2839393 -0.6850552 0.0492736 -0.0220819
GB42887 protein NPC2 homolog 11.895962 0.4934256 0.1171569 0.8267574 -0.2535760
GB43984 xenotropic and polytropic retrovirus receptor 1 homolog 11.711923 -0.0394515 0.0389923 0.0492826 0.1485743
GB48252 dihydrofolate reductase isoform X2 11.676320 0.2476259 0.2239091 -0.1962494 0.1041595
GB47270 cytochrome P450 4C1 11.593087 0.3133208 0.1872647 0.7449695 0.5041494
GB48109 retinoid-inducible serine carboxypeptidase-like isoform X3 11.544591 0.9904184 0.1527256 -0.4756137 0.2243044
GB54313 uncharacterized protein LOC413386 isoform X3 11.417055 -0.2681125 0.0458400 -0.5743109 -0.0318130
GB51913 thymidylate kinase-like isoform X2 11.334845 -0.3730554 0.3081842 -0.1084622 0.0965259
GB44503 uncharacterized protein LOC727423 isoform X2 11.287468 0.8326731 -0.2057741 -0.1159152 0.0800218
GB53229 WAS protein family homolog 1-like 11.254827 0.0009783 0.1385308 0.0844486 -0.0924363
GB51834 sodium-dependent nutrient amino acid transporter 1-like 11.166136 -0.3531060 -0.2620501 0.0808984 0.0511710
GB52505 chaoptin-like 10.968009 0.4587636 -0.0083482 -0.3768354 0.1096745
GB52275 pancreatic lipase-related protein 2-like 10.793842 0.1098269 0.2574445 -0.4376261 0.1596069
GB55302 trehalose transporter 1 isoform X6 10.667963 -0.0677498 -0.1155692 -0.2214355 0.3081366
102654789 uncharacterized protein LOC102654789 10.667109 -0.0584019 -0.3278716 -0.6095776 0.0498065
GB42616 beta-hexosaminidase subunit beta-like 10.368794 -0.2289562 0.1451877 0.0621008 0.0620511
GB54153 uncharacterized protein LOC100576236 isoform X1 10.118213 -0.0809921 -0.1347052 -1.4023742 -0.1316166
GB47327 lipid phosphate phosphohydrolase 3-like 10.058571 0.2857168 -0.2176489 0.1057685 -0.0934929
GB50021 exonuclease 3’-5’ domain-containing protein 2-like isoform X1 9.842047 -0.0736605 0.2350361 0.2707233 0.0938046
GB40344 uncharacterized protein LOC552242 9.828621 0.1172944 -0.8017426 -0.2242850 0.5032930
GB49929 laminin subunit alpha 9.561491 0.5340516 0.2430509 -0.5370697 -0.6102948
GB44663 homeobox protein Nkx-2.4-like 9.551657 0.1394744 -0.3654465 0.1719647 -0.1904368
GB51107 uncharacterized protein LOC100578731 isoform X1 9.377499 0.4302073 0.1834154 0.1378654 -0.1713280
GB50524 uncharacterized protein LOC726417 8.929495 -0.0588231 0.0511584 -1.3909039 -0.1613334
GB51696 hexamerin 70c precursor 8.783477 -0.0474407 -0.2625302 0.0807997 0.5193354
GB51195 protein abrupt-like isoform X5 8.448029 -0.0648071 0.2780828 -0.3448047 0.0069477
GB46800 uncharacterized protein LOC100577231 8.330772 -0.6305159 -0.0697162 0.5306095 0.0739981
GB52656 uncharacterized protein LOC552154 8.299683 0.5834384 -0.2149017 -0.5531551 -0.1221217
GB42799 protein takeout-like 8.250769 -0.2869070 0.2517661 -1.5197911 -1.0284651
GB42426 glutamyl aminopeptidase-like isoform X2 7.939937 0.7268796 0.4365634 -0.6505219 0.0556743
GB53155 maternal embryonic leucine zipper kinase-like 7.859620 -0.0641905 0.0686990 3.1684473 0.0911321
GB44967 GTP:AMP phosphotransferase AK3, mitochondrial isoform X1 7.715168 -0.2241576 -0.0260340 1.0680177 0.3088382
GB48079 trypsin-7 7.662906 0.7889055 -0.6491093 -0.9266060 0.0966946
102656088 uncharacterized protein LOC102656088 7.565171 1.6565192 -0.7683197 -0.7692478 -0.7298828
GB50434 proton-coupled amino acid transporter 1-like 7.268236 0.0112121 -0.1261022 -0.0116264 -0.2000854
GB49813 SUMO-activating enzyme subunit 1 7.001295 0.5203949 0.2339421 0.6507883 0.1731960
GB43181 uncharacterized protein LOC552799 isoform X2 6.971888 0.5939354 0.7192746 -0.8612463 0.0416577
GB46693 WD repeat-containing protein 65-like 6.867550 0.1122710 -0.0684919 0.1286625 -0.1355103
GB47181 NADH dehydrogenase [ubiquinone] iron-sulfur protein 4, mitochondrial 6.863152 -0.1128277 -0.0754332 0.5035167 0.1284447
GB52667 uncharacterized protein LOC552202 isoform X6 6.664971 -0.2443954 -0.0018447 -1.1119964 -0.0773408
GB53401 protein fosB isoform X1 6.443355 0.0228858 -0.1389772 0.0142738 0.1133762
GB47507 histone H2A-like 6.019835 -0.6332116 0.2794373 -0.2087029 -0.1453361
GB45458 UDP-glucose 6-dehydrogenase-like isoform X2 5.705610 -0.0389463 -0.0525780 -0.3343070 -0.2095720
GB41782 LOW QUALITY PROTEIN: glycine dehydrogenase [decarboxylating], mitochondrial-like 5.448141 0.1849845 -0.2525962 -0.0070789 -0.1010127
GB54426 transmembrane protein 205-like 5.184689 -0.0505523 0.1720915 0.0864230 -0.0824220
GB43591 uncharacterized protein LOC408443 4.927475 0.4363105 0.2200117 -0.3238923 0.1074204
GB46298 endocuticle structural glycoprotein SgAbd-8-like isoform X2 3.339703 0.2037923 -0.6881852 -0.0825740 0.1612789

Inspect the gene list for the pheromone-sensitive module 9

Table S35: List of all the genes in Module 9, ranked by their within-module connectivity, k. The latter four columns give the Log\(_2\) fold-change in expression in response to queen pheromone in each of the four species.

inspect.module.genes(9) %>% 
  mutate(am_fc=log2(am_fc), bt_fc=log2(bt_fc), lf_fc=log2(lf_fc), ln_fc=log2(ln_fc)) %>% 
  rename(Gene=gene, Name=name) %>% 
  kable.table()
Gene Name k am_fc bt_fc lf_fc ln_fc
GB49598 RNA-binding protein Rsf1 3.4281703 0.3056885 -0.0032899 0.1101417 0.0851146
GB49355 uncharacterized protein LOC100576266 isoform X2 3.2620545 0.3093869 0.0572808 -0.1561239 0.1319324
GB51008 metaxin-2-like isoform 2 3.2002938 0.4439731 -0.1469924 0.0424195 0.1446767
GB52735 DAZ-associated protein 2-like isoform X2 2.9721946 0.2871285 0.0231294 0.0623909 -0.1752350
GB55970 proliferating cell nuclear antigen 2.8130746 0.3776271 0.2351576 0.0776321 0.0776232
551833 PAXIP1-associated glutamate-rich protein 1-like isoform 2 2.7565876 0.4962252 0.0926024 0.0590149 0.2492689
GB43092 cyclin-dependent kinase 5 2.5960809 0.3844390 0.0216430 0.0951021 0.1433308
GB55381 centrosomal protein of 97 kDa isoform X2 2.5582953 0.2955124 -0.0548547 0.1869490 0.1357882
GB43232 transmembrane protein 222-like isoform 1 2.3398175 0.5861394 0.0458418 0.1933063 0.2422045
GB50724 peptidyl-tRNA hydrolase 2, mitochondrial-like isoform 1 2.2475846 0.7085344 -0.0764084 0.0647428 0.1173188
GB51226 tyrosine-protein kinase CSK isoform X4 2.2239789 0.5181445 0.0036483 0.2021335 0.1570482
GB56003 methyltransferase-like protein 14 homolog 2.2171705 0.3353470 0.1482768 0.1276493 0.1038143
GB48128 DNA-directed RNA polymerase III subunit RPC8-like isoform 1 2.1261420 0.7927715 0.1807240 -0.1997985 0.1943152
GB42319 uncharacterized protein LOC409105 isoform 1 2.1081864 0.7613151 -0.1786302 0.0944737 0.3063722
GB45649 adenosine 3’-phospho 5’-phosphosulfate transporter 1 2.0383947 0.5325883 -0.0623392 0.1488054 0.2109308
GB43086 uncharacterized protein LOC726486 1.9692909 0.6676944 0.0549481 0.1238370 0.1069750
GB45657 cdc42 homolog isoform X2 1.9443700 0.4128119 0.1648899 0.1727575 0.0882596
GB53270 UPF0428 protein CXorf56 homolog isoformX2 1.9439132 -0.0053964 0.0902614 0.0955928 0.1557436
GB48852 heterogeneous nuclear ribonucleoprotein H-like isoform X1 1.9171405 0.3943774 -0.0242347 0.1867469 0.1629403
GB45560 2-aminoethanethiol dioxygenase-like isoform X2 1.8928212 0.5646965 0.0858905 0.2044355 0.1964693
GB53957 U6 snRNA-associated Sm-like protein LSm1-like 1.8732559 1.2758936 0.1485275 0.0654838 0.1025379
GB55241 myosin-9-like isoform X2 1.8577528 0.3826838 0.0273981 0.1613124 0.3355618
GB42726 lysosomal protein NCU-G1-A-like 1.8538445 0.1961158 -0.1161535 0.0827387 0.1842311
GB52929 soluble guanylyl cyclase alpha 1 subunit 1.8202355 0.8632355 0.0679563 0.2472309 0.1991959
GB55098 progestin and adipoQ receptor family member 4-like isoform X3 1.8069386 1.0981696 0.0958375 0.2837369 0.3395738
GB50885 uncharacterized protein LOC409648 1.8009421 0.5217942 -0.1408814 0.1076250 -0.0919353
GB54279 cleavage and polyadenylation specificity factor subunit 4 1.7698409 0.3124242 0.3549593 1.6577375 0.2521921
GB45810 locomotion-related protein Hikaru genki isoform X4 1.7456427 0.4274473 -0.0495554 0.1897961 0.1299238
GB54147 loss of heterozygosity 12 chromosomal region 1 protein homolog 1.7319102 0.4424770 -0.0518968 0.1119449 0.0806514
GB48175 probable cytochrome P450 305a1 1.7158930 1.5793489 0.0957169 0.0666737 0.2220252
GB50090 adenosine deaminase acting on RNA 1.7017820 0.2845926 -0.0201237 0.2675177 0.3162340
GB55831 aromatic-L-amino-acid decarboxylase isoform X2 1.6395161 0.7455077 0.7384633 0.0929703 0.2855078
GB52236 leucine-rich repeat-containing protein C10orf11 homolog isoform X1 1.6041255 0.2352825 0.0773345 0.0243112 0.1325469
GB44143 oxidative stress-induced growth inhibitor 1-like isoform X1 1.5781579 0.4074280 0.0477067 0.0904485 0.0514744
GB42224 leucine-rich repeat and calponin homology domain-containing protein 1-like isoform X2 1.5751039 0.4417497 -0.0693594 1.2318066 0.2994614
GB46734 mitochondrial import inner membrane translocase subunit TIM14-like isoform X3 1.5718335 0.1173025 0.0125511 0.2021870 0.2728669
GB43817 atrial natriuretic peptide receptor 1-like 1.5134486 0.4326071 0.1235643 0.1802794 0.0892441
GB50722 phospholipase A1 member A-like 0.7527136 1.8995474 0.3289060 -0.0744550 0.5503768

R session information

This section shows the operating system and R packages used to produce this document.

sessionInfo() %>% pander()

R version 3.3.2 (2016-10-31)

**Platform:** x86_64-apple-darwin13.4.0 (64-bit)

locale: en_AU.UTF-8||en_AU.UTF-8||en_AU.UTF-8||C||en_AU.UTF-8||en_AU.UTF-8

attached base packages: stats4, parallel, stats, graphics, grDevices, utils, datasets, methods and base

other attached packages: GO.db(v.3.4.0), KEGG.db(v.3.2.3), bindrcpp(v.0.2), knitr(v.1.20), kableExtra(v.0.8.0.0001), pander(v.0.6.0), sva(v.3.22.0), genefilter(v.1.56.0), mgcv(v.1.8-15), nlme(v.3.1-128), MuMIn(v.1.15.6), ecodist(v.1.2.9), gplots(v.3.0.1), ggjoy(v.0.3.0), RColorBrewer(v.1.1-2), gridExtra(v.2.2.1), ggdendro(v.0.1-20), ggrepel(v.0.6.5), ggplot2(v.2.2.1), stringr(v.1.2.0), tidyr(v.0.7.2), dplyr(v.0.7.4), reshape2(v.1.4.3), RSQLite(v.1.1-2), WGCNA(v.1.51), fastcluster(v.1.1.22), dynamicTreeCut(v.1.63-1), GOstats(v.2.40.0), graph(v.1.52.0), Category(v.2.40.0), Matrix(v.1.2-12), AnnotationDbi(v.1.36.2), IRanges(v.2.8.2), S4Vectors(v.0.12.2), Biobase(v.2.34.0) and BiocGenerics(v.0.20.0)

loaded via a namespace (and not attached): bitops(v.1.0-6), matrixStats(v.0.52.2), httr(v.1.3.1), doParallel(v.1.0.10), rprojroot(v.1.2), tools(v.3.3.2), backports(v.1.0.5), R6(v.2.2.2), rpart(v.4.1-10), KernSmooth(v.2.23-15), Hmisc(v.4.0-2), DBI(v.0.5-1), lazyeval(v.0.2.0), colorspace(v.1.3-2), nnet(v.7.3-12), preprocessCore(v.1.36.0), rvest(v.0.3.2), htmlTable(v.1.9), xml2(v.1.2.0), caTools(v.1.17.1), scales(v.0.5.0), checkmate(v.1.8.2), readr(v.1.1.1), RBGL(v.1.50.0), digest(v.0.6.13), foreign(v.0.8-67), rmarkdown(v.1.8), AnnotationForge(v.1.16.1), base64enc(v.0.1-3), pkgconfig(v.2.0.1), htmltools(v.0.3.6), highr(v.0.6), dbplyr(v.1.1.0), htmlwidgets(v.0.8), rlang(v.0.1.4), rstudioapi(v.0.7), impute(v.1.48.0), bindr(v.0.1), gtools(v.3.5.0), acepack(v.1.4.1), RCurl(v.1.95-4.8), magrittr(v.1.5), Formula(v.1.2-1), Rcpp(v.0.12.14), munsell(v.0.4.3), stringi(v.1.1.2), yaml(v.2.1.14), MASS(v.7.3-45), plyr(v.1.8.4), grid(v.3.3.2), gdata(v.2.17.0), lattice(v.0.20-34), splines(v.3.3.2), annotate(v.1.52.1), hms(v.0.3), codetools(v.0.2-15), XML(v.3.98-1.5), glue(v.1.2.0), evaluate(v.0.10), latticeExtra(v.0.6-28), data.table(v.1.10.4-3), foreach(v.1.4.4), gtable(v.0.2.0), purrr(v.0.2.4), assertthat(v.0.2.0), xtable(v.1.8-2), viridisLite(v.0.2.0), survival(v.2.40-1), tibble(v.1.3.4), iterators(v.1.0.9), memoise(v.1.0.0), cluster(v.2.0.5) and GSEABase(v.1.36.0)